hgext/convert/convcmd.py

43076:2372284d9457

monotone_source = monotone.monotone_source
p4_source = p4.p4_source
svn_sink = subversion.svn_sink
svn_source = subversion.svn_source

orig_encoding = 'ascii'


def recode(s):
    if isinstance(s, pycompat.unicode):
        return s.encode(pycompat.sysstr(orig_encoding), 'replace')

    # If branch is None or empty, this commit is coming from the source
    # repository's default branch and destined for the default branch in the
    # destination repository. For such commits, using a literal "default"
    # in branchmap below allows the user to map "default" to an alternate
    # default branch in the destination repository.
    branch = branchmap.get(branch or 'default', branch)
    # At some point we used "None" literal to denote the default branch,
    # attempt to use that for backward compatibility.
    if not branch:
        branch = branchmap.get('None', branch)
    return branch


source_converters = [
    ('cvs', convert_cvs, 'branchsort'),
    ('git', convert_git, 'branchsort'),
    ('svn', svn_source, 'branchsort'),
    ('hg', mercurial_source, 'sourcesort'),
    ('darcs', darcs_source, 'branchsort'),
    ('mtn', monotone_source, 'branchsort'),
    ('gnuarch', gnuarch_source, 'branchsort'),
    ('bzr', bzr_source, 'branchsort'),
    ('p4', p4_source, 'branchsort'),
]

sink_converters = [
    ('hg', mercurial_sink),
    ('svn', svn_sink),
]


def convertsource(ui, path, type, revs):
    exceptions = []
    if type and type not in [s[0] for s in source_converters]:
        raise error.Abort(_('%s: invalid source repository type') % type)
    for name, source, sortmode in source_converters:
        try:
            if not type or name == type:
                return source(ui, name, path, revs), sortmode
        except (NoRepo, MissingTool) as inst:
            exceptions.append(inst)
    if not ui.quiet:
        for inst in exceptions:
            ui.write("%s\n" % pycompat.bytestr(inst.args[0]))
    raise error.Abort(_('%s: missing or unsupported repository') % path)


def convertsink(ui, path, type):
    if type and type not in [s[0] for s in sink_converters]:
        raise error.Abort(_('%s: invalid destination repository type') % type)
    for name, sink in sink_converters:
        try:
            if not type or name == type:
                return sink(ui, name, path)
        except NoRepo as inst:
            ui.note(_("convert: %s\n") % inst)
        except MissingTool as inst:
            raise error.Abort('%s\n' % inst)
    raise error.Abort(_('%s: unknown repository type') % path)


class progresssource(object):
    def __init__(self, ui, source, filecount):
        self.ui = ui
        self.source = source
        self.progress = ui.makeprogress(
            _('getting files'), unit=_('files'), total=filecount
        )

    def getfile(self, file, rev):
        self.progress.increment(item=file)
        return self.source.getfile(file, rev)

        # Read first the dst author map if any
        authorfile = self.dest.authorfile()
        if authorfile and os.path.exists(authorfile):
            self.readauthormap(authorfile)
        # Extend/Override with new author map if necessary
        if opts.get('authormap'):
            self.readauthormap(opts.get('authormap'))
            self.authorfile = self.dest.authorfile()

        self.splicemap = self.parsesplicemap(opts.get('splicemap'))
        self.branchmap = mapfile(ui, opts.get('branchmap'))

    def parsesplicemap(self, path):
        """ check and validate the splicemap format and
            return a child/parents dictionary.
            Format checking has two parts.

        if not path:
            return {}
        m = {}
        try:
            fp = open(path, 'rb')
            for i, line in enumerate(util.iterfile(fp)):
                line = line.splitlines()[0].rstrip()
                if not line:
                    # Ignore blank lines
                    continue
                # split line
                lex = common.shlexer(data=line, whitespace=',')
                line = list(lex)
                # check number of parents
                if not (2 <= len(line) <= 3):
                    raise error.Abort(
                        _(
                            'syntax error in %s(%d): child parent1'
                            '[,parent2] expected'
                        )
                        % (path, i + 1)
                    )
                for part in line:
                    self.source.checkrevformat(part)

                else:
                    m[child] = p1 + p2
        # if file does not exist or error reading, exit
        except IOError:
            raise error.Abort(
                _('splicemap file not found or error reading %s:') % path
            )
        return m

    def walktree(self, heads):
        '''Return a mapping that identifies the uncommitted parents of every

        visit = list(heads)
        known = set()
        parents = {}
        numcommits = self.source.numcommits()
        progress = self.ui.makeprogress(
            _('scanning'), unit=_('revisions'), total=numcommits
        )
        while visit:
            n = visit.pop(0)
            if n in known:
                continue

            if c not in parents:
                if not self.dest.hascommitforsplicemap(self.map.get(c, c)):
                    # Could be in source but not converted during this run
                    self.ui.warn(
                        _(
                            'splice map revision %s is not being '
                            'converted, ignoring\n'
                        )
                        % c
                    )
                continue
            pc = []

                # We do not have to wait for nodes already in dest.
                if self.dest.hascommitforsplicemap(self.map.get(p, p)):
                    continue
                # Parent is not in dest and not being converted, not good
                if p not in parents:
                    raise error.Abort(_('unknown splice map parent: %s') % p)
                pc.append(p)
            parents[c] = pc

    def toposort(self, parents, sortmode):
        '''Return an ordering such that every uncommitted changeset is

            return picknext

        def makeclosesorter():
            """Close order sort."""
            keyfn = lambda n: (
                'close' not in self.commitcache[n].extra,
                self.commitcache[n].sortkey,
            )

            def picknext(nodes):
                return sorted(nodes, key=keyfn)[0]

            def picknext(nodes):
                return min([(getdate(n), n) for n in nodes])[1]

            return picknext

        if sortmode == 'branchsort':
            picknext = makebranchsorter()
        elif sortmode == 'datesort':
            picknext = makedatesorter()
        elif sortmode == 'sourcesort':
            picknext = makesourcesorter()
        elif sortmode == 'closesort':
            picknext = makeclosesorter()
        else:
            raise error.Abort(_('unknown sort mode: %s') % sortmode)

        children, actives = mapchildren(parents)

        s = []
        pendings = {}

                    pendings[c] = [p for p in parents[c] if p not in self.map]
                try:
                    pendings[c].remove(n)
                except ValueError:
                    raise error.Abort(
                        _('cycle detected between %s and %s')
                        % (recode(c), recode(n))
                    )
                if not pendings[c]:
                    # Parents are converted, node is eligible
                    actives.insert(0, c)
                    pendings[c] = None

        if len(s) != len(parents):
            raise error.Abort(_("not all revisions were sorted"))

        return s

    def writeauthormap(self):
        authorfile = self.authorfile
        if authorfile:
            self.ui.status(_('writing author map file %s\n') % authorfile)
            ofile = open(authorfile, 'wb+')
            for author in self.authors:
                ofile.write(
                    util.tonativeeol("%s=%s\n" % (author, self.authors[author]))
                )
            ofile.close()

    def readauthormap(self, authorfile):
        afile = open(authorfile, 'rb')
        for line in afile:

            line = line.strip()
            if not line or line.startswith('#'):
                continue

            try:
                srcauthor, dstauthor = line.split('=', 1)
            except ValueError:
                msg = _('ignoring bad line in author map file %s: %s\n')
                self.ui.warn(msg % (authorfile, line.rstrip()))
                continue

            srcauthor = srcauthor.strip()
            dstauthor = dstauthor.strip()
            if self.authors.get(srcauthor) in (None, dstauthor):
                msg = _('mapping author %s to %s\n')
                self.ui.debug(msg % (srcauthor, dstauthor))
                self.authors[srcauthor] = dstauthor
                continue

            m = _('overriding mapping for author %s, was %s, will be %s\n')
            self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))

        afile.close()

    def cachecommit(self, rev):

        self.commitcache[rev] = commit
        return commit

    def copy(self, rev):
        commit = self.commitcache[rev]
        full = self.opts.get('full')
        changes = self.source.getchanges(rev, full)
        if isinstance(changes, bytes):
            if changes == SKIPREV:
                dest = SKIPREV
            else:

                )
        self.dest.setbranch(commit.branch, pbranches)
        try:
            parents = self.splicemap[rev]
            self.ui.status(
                _('spliced in %s as parents of %s\n')
                % (_(' and ').join(parents), rev)
            )
            parents = [self.map.get(p, p) for p in parents]
        except KeyError:
            parents = [b[0] for b in pbranches]
            parents.extend(

    def convert(self, sortmode):
        try:
            self.source.before()
            self.dest.before()
            self.source.setrevmap(self.map)
            self.ui.status(_("scanning source...\n"))
            heads = self.source.getheads()
            parents = self.walktree(heads)
            self.mergesplicemap(parents, self.splicemap)
            self.ui.status(_("sorting...\n"))
            t = self.toposort(parents, sortmode)
            num = len(t)
            c = None

            self.ui.status(_("converting...\n"))
            progress = self.ui.makeprogress(
                _('converting'), unit=_('revisions'), total=len(t)
            )
            for i, c in enumerate(t):
                num -= 1
                desc = self.commitcache[c].desc
                if "\n" in desc:
                    desc = desc.splitlines()[0]
                # convert log message to local encoding without using
                # tolocal() because the encoding.encoding convert()
                # uses is 'utf-8'
                self.ui.status("%d %s\n" % (num, recode(desc)))
                self.ui.note(_("source: %s\n") % recode(c))
                progress.update(i)
                self.copy(c)
            progress.complete()

            if not self.ui.configbool('convert', 'skiptags'):
                tags = self.source.gettags()
                ctags = {}
                for k in tags:
                    v = tags[k]
                    if self.map.get(v, SKIPREV) != SKIPREV:

def convert(ui, src, dest=None, revmapfile=None, **opts):
    opts = pycompat.byteskwargs(opts)
    global orig_encoding
    orig_encoding = encoding.encoding
    encoding.encoding = 'UTF-8'

    # support --authors as an alias for --authormap
    if not opts.get('authormap'):
        opts['authormap'] = opts.get('authors')

    if not dest:
        dest = hg.defaultdest(src) + "-hg"
        ui.status(_("assuming destination %s\n") % dest)

    destc = convertsink(ui, dest, opts.get('dest_type'))
    destc = scmutil.wrapconvertsink(destc)

    try:
        srcc, defaultsort = convertsource(
            ui, src, opts.get('source_type'), opts.get('rev')
        )
    except Exception:
        for path in destc.created:
            shutil.rmtree(path, True)
        raise

    sortmodes = ('branchsort', 'datesort', 'sourcesort', 'closesort')
    sortmode = [m for m in sortmodes if opts.get(m)]
    if len(sortmode) > 1:
        raise error.Abort(_('more than one sort mode specified'))
    if sortmode:
        sortmode = sortmode[0]
    else:
        sortmode = defaultsort

    if sortmode == 'sourcesort' and not srcc.hasnativeorder():
        raise error.Abort(
            _('--sourcesort is not supported by this data source')
        )
    if sortmode == 'closesort' and not srcc.hasnativeclose():
        raise error.Abort(_('--closesort is not supported by this data source'))

    fmap = opts.get('filemap')
    if fmap:
        srcc = filemap.filemap_source(ui, srcc, fmap)
        destc.setfilemapmode(True)

    if not revmapfile:

43077:687b865b95ad

monotone_source = monotone.monotone_source
p4_source = p4.p4_source
svn_sink = subversion.svn_sink
svn_source = subversion.svn_source

orig_encoding = b'ascii'


def recode(s):
    if isinstance(s, pycompat.unicode):
        return s.encode(pycompat.sysstr(orig_encoding), 'replace')

    # If branch is None or empty, this commit is coming from the source
    # repository's default branch and destined for the default branch in the
    # destination repository. For such commits, using a literal "default"
    # in branchmap below allows the user to map "default" to an alternate
    # default branch in the destination repository.
    branch = branchmap.get(branch or b'default', branch)
    # At some point we used "None" literal to denote the default branch,
    # attempt to use that for backward compatibility.
    if not branch:
        branch = branchmap.get(b'None', branch)
    return branch


source_converters = [
    (b'cvs', convert_cvs, b'branchsort'),
    (b'git', convert_git, b'branchsort'),
    (b'svn', svn_source, b'branchsort'),
    (b'hg', mercurial_source, b'sourcesort'),
    (b'darcs', darcs_source, b'branchsort'),
    (b'mtn', monotone_source, b'branchsort'),
    (b'gnuarch', gnuarch_source, b'branchsort'),
    (b'bzr', bzr_source, b'branchsort'),
    (b'p4', p4_source, b'branchsort'),
]

sink_converters = [
    (b'hg', mercurial_sink),
    (b'svn', svn_sink),
]


def convertsource(ui, path, type, revs):
    exceptions = []
    if type and type not in [s[0] for s in source_converters]:
        raise error.Abort(_(b'%s: invalid source repository type') % type)
    for name, source, sortmode in source_converters:
        try:
            if not type or name == type:
                return source(ui, name, path, revs), sortmode
        except (NoRepo, MissingTool) as inst:
            exceptions.append(inst)
    if not ui.quiet:
        for inst in exceptions:
            ui.write(b"%s\n" % pycompat.bytestr(inst.args[0]))
    raise error.Abort(_(b'%s: missing or unsupported repository') % path)


def convertsink(ui, path, type):
    if type and type not in [s[0] for s in sink_converters]:
        raise error.Abort(_(b'%s: invalid destination repository type') % type)
    for name, sink in sink_converters:
        try:
            if not type or name == type:
                return sink(ui, name, path)
        except NoRepo as inst:
            ui.note(_(b"convert: %s\n") % inst)
        except MissingTool as inst:
            raise error.Abort(b'%s\n' % inst)
    raise error.Abort(_(b'%s: unknown repository type') % path)


class progresssource(object):
    def __init__(self, ui, source, filecount):
        self.ui = ui
        self.source = source
        self.progress = ui.makeprogress(
            _(b'getting files'), unit=_(b'files'), total=filecount
        )

    def getfile(self, file, rev):
        self.progress.increment(item=file)
        return self.source.getfile(file, rev)

        # Read first the dst author map if any
        authorfile = self.dest.authorfile()
        if authorfile and os.path.exists(authorfile):
            self.readauthormap(authorfile)
        # Extend/Override with new author map if necessary
        if opts.get(b'authormap'):
            self.readauthormap(opts.get(b'authormap'))
            self.authorfile = self.dest.authorfile()

        self.splicemap = self.parsesplicemap(opts.get(b'splicemap'))
        self.branchmap = mapfile(ui, opts.get(b'branchmap'))

    def parsesplicemap(self, path):
        """ check and validate the splicemap format and
            return a child/parents dictionary.
            Format checking has two parts.

        if not path:
            return {}
        m = {}
        try:
            fp = open(path, b'rb')
            for i, line in enumerate(util.iterfile(fp)):
                line = line.splitlines()[0].rstrip()
                if not line:
                    # Ignore blank lines
                    continue
                # split line
                lex = common.shlexer(data=line, whitespace=b',')
                line = list(lex)
                # check number of parents
                if not (2 <= len(line) <= 3):
                    raise error.Abort(
                        _(
                            b'syntax error in %s(%d): child parent1'
                            b'[,parent2] expected'
                        )
                        % (path, i + 1)
                    )
                for part in line:
                    self.source.checkrevformat(part)

                else:
                    m[child] = p1 + p2
        # if file does not exist or error reading, exit
        except IOError:
            raise error.Abort(
                _(b'splicemap file not found or error reading %s:') % path
            )
        return m

    def walktree(self, heads):
        '''Return a mapping that identifies the uncommitted parents of every

        visit = list(heads)
        known = set()
        parents = {}
        numcommits = self.source.numcommits()
        progress = self.ui.makeprogress(
            _(b'scanning'), unit=_(b'revisions'), total=numcommits
        )
        while visit:
            n = visit.pop(0)
            if n in known:
                continue

            if c not in parents:
                if not self.dest.hascommitforsplicemap(self.map.get(c, c)):
                    # Could be in source but not converted during this run
                    self.ui.warn(
                        _(
                            b'splice map revision %s is not being '
                            b'converted, ignoring\n'
                        )
                        % c
                    )
                continue
            pc = []

                # We do not have to wait for nodes already in dest.
                if self.dest.hascommitforsplicemap(self.map.get(p, p)):
                    continue
                # Parent is not in dest and not being converted, not good
                if p not in parents:
                    raise error.Abort(_(b'unknown splice map parent: %s') % p)
                pc.append(p)
            parents[c] = pc

    def toposort(self, parents, sortmode):
        '''Return an ordering such that every uncommitted changeset is

            return picknext

        def makeclosesorter():
            """Close order sort."""
            keyfn = lambda n: (
                b'close' not in self.commitcache[n].extra,
                self.commitcache[n].sortkey,
            )

            def picknext(nodes):
                return sorted(nodes, key=keyfn)[0]

            def picknext(nodes):
                return min([(getdate(n), n) for n in nodes])[1]

            return picknext

        if sortmode == b'branchsort':
            picknext = makebranchsorter()
        elif sortmode == b'datesort':
            picknext = makedatesorter()
        elif sortmode == b'sourcesort':
            picknext = makesourcesorter()
        elif sortmode == b'closesort':
            picknext = makeclosesorter()
        else:
            raise error.Abort(_(b'unknown sort mode: %s') % sortmode)

        children, actives = mapchildren(parents)

        s = []
        pendings = {}

                    pendings[c] = [p for p in parents[c] if p not in self.map]
                try:
                    pendings[c].remove(n)
                except ValueError:
                    raise error.Abort(
                        _(b'cycle detected between %s and %s')
                        % (recode(c), recode(n))
                    )
                if not pendings[c]:
                    # Parents are converted, node is eligible
                    actives.insert(0, c)
                    pendings[c] = None

        if len(s) != len(parents):
            raise error.Abort(_(b"not all revisions were sorted"))

        return s

    def writeauthormap(self):
        authorfile = self.authorfile
        if authorfile:
            self.ui.status(_(b'writing author map file %s\n') % authorfile)
            ofile = open(authorfile, b'wb+')
            for author in self.authors:
                ofile.write(
                    util.tonativeeol(
                        b"%s=%s\n" % (author, self.authors[author])
                    )
                )
            ofile.close()

    def readauthormap(self, authorfile):
        afile = open(authorfile, b'rb')
        for line in afile:

            line = line.strip()
            if not line or line.startswith(b'#'):
                continue

            try:
                srcauthor, dstauthor = line.split(b'=', 1)
            except ValueError:
                msg = _(b'ignoring bad line in author map file %s: %s\n')
                self.ui.warn(msg % (authorfile, line.rstrip()))
                continue

            srcauthor = srcauthor.strip()
            dstauthor = dstauthor.strip()
            if self.authors.get(srcauthor) in (None, dstauthor):
                msg = _(b'mapping author %s to %s\n')
                self.ui.debug(msg % (srcauthor, dstauthor))
                self.authors[srcauthor] = dstauthor
                continue

            m = _(b'overriding mapping for author %s, was %s, will be %s\n')
            self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))

        afile.close()

    def cachecommit(self, rev):

        self.commitcache[rev] = commit
        return commit

    def copy(self, rev):
        commit = self.commitcache[rev]
        full = self.opts.get(b'full')
        changes = self.source.getchanges(rev, full)
        if isinstance(changes, bytes):
            if changes == SKIPREV:
                dest = SKIPREV
            else:

                )
        self.dest.setbranch(commit.branch, pbranches)
        try:
            parents = self.splicemap[rev]
            self.ui.status(
                _(b'spliced in %s as parents of %s\n')
                % (_(b' and ').join(parents), rev)
            )
            parents = [self.map.get(p, p) for p in parents]
        except KeyError:
            parents = [b[0] for b in pbranches]
            parents.extend(

    def convert(self, sortmode):
        try:
            self.source.before()
            self.dest.before()
            self.source.setrevmap(self.map)
            self.ui.status(_(b"scanning source...\n"))
            heads = self.source.getheads()
            parents = self.walktree(heads)
            self.mergesplicemap(parents, self.splicemap)
            self.ui.status(_(b"sorting...\n"))
            t = self.toposort(parents, sortmode)
            num = len(t)
            c = None

            self.ui.status(_(b"converting...\n"))
            progress = self.ui.makeprogress(
                _(b'converting'), unit=_(b'revisions'), total=len(t)
            )
            for i, c in enumerate(t):
                num -= 1
                desc = self.commitcache[c].desc
                if b"\n" in desc:
                    desc = desc.splitlines()[0]
                # convert log message to local encoding without using
                # tolocal() because the encoding.encoding convert()
                # uses is 'utf-8'
                self.ui.status(b"%d %s\n" % (num, recode(desc)))
                self.ui.note(_(b"source: %s\n") % recode(c))
                progress.update(i)
                self.copy(c)
            progress.complete()

            if not self.ui.configbool(b'convert', b'skiptags'):
                tags = self.source.gettags()
                ctags = {}
                for k in tags:
                    v = tags[k]
                    if self.map.get(v, SKIPREV) != SKIPREV:

def convert(ui, src, dest=None, revmapfile=None, **opts):
    opts = pycompat.byteskwargs(opts)
    global orig_encoding
    orig_encoding = encoding.encoding
    encoding.encoding = b'UTF-8'

    # support --authors as an alias for --authormap
    if not opts.get(b'authormap'):
        opts[b'authormap'] = opts.get(b'authors')

    if not dest:
        dest = hg.defaultdest(src) + b"-hg"
        ui.status(_(b"assuming destination %s\n") % dest)

    destc = convertsink(ui, dest, opts.get(b'dest_type'))
    destc = scmutil.wrapconvertsink(destc)

    try:
        srcc, defaultsort = convertsource(
            ui, src, opts.get(b'source_type'), opts.get(b'rev')
        )
    except Exception:
        for path in destc.created:
            shutil.rmtree(path, True)
        raise

    sortmodes = (b'branchsort', b'datesort', b'sourcesort', b'closesort')
    sortmode = [m for m in sortmodes if opts.get(m)]
    if len(sortmode) > 1:
        raise error.Abort(_(b'more than one sort mode specified'))
    if sortmode:
        sortmode = sortmode[0]
    else:
        sortmode = defaultsort

    if sortmode == b'sourcesort' and not srcc.hasnativeorder():
        raise error.Abort(
            _(b'--sourcesort is not supported by this data source')
        )
    if sortmode == b'closesort' and not srcc.hasnativeclose():
        raise error.Abort(
            _(b'--closesort is not supported by this data source')
        )

    fmap = opts.get(b'filemap')
    if fmap:
        srcc = filemap.filemap_source(ui, srcc, fmap)
        destc.setfilemapmode(True)

    if not revmapfile: