comparison hgext/convert/bzr.py @ 16059:f5b6046f6ce8

convert/bzr: expect unicode metadata, encode in UTF-8 (issue3232)

Before this patch, metadata and file names were interpreted like:
- unicode objects were converted to UTF-8
- non unicode objects were left unchanged

Looking at the code and bzr being known for transcoding filenames, we expect
everything to be returned as unicode objects, and we want to encode them in
UTF-8, like the subversion source does. To do that, we just remove the custom
implementation of .recode().

16057:db4b0532dbf2

            self._parentids[version] = parents

        return commit(parents=parents,
                date='%d %d' % (rev.timestamp, -rev.timezone),
                author=self.recode(rev.committer),
                # bzr returns bytestrings or unicode, depending on the content
                desc=self.recode(rev.message),
                rev=version)

    def gettags(self):
        if not self.branch.supports_tags():

                # no futher changes, go to the next change
                continue

            # we got unicode paths, need to convert them
            path, topath = [self.recode(part) for part in paths]
            seen.add(path or topath)

            if topath is None:
                # file deleted
                changes.append((path, revid))

        <http://bazaar-vcs.org/GhostRevision>
        """
        parentmap = self.sourcerepo.get_parent_map(ids)
        parents = tuple([parent for parent in ids if parent in parentmap])
        return parents

    def recode(self, s, encoding=None):
        """This version of recode tries to encode unicode to bytecode,
        and preferably using the UTF-8 codec.
        Other types than Unicode are silently returned, this is by
        intention, e.g. the None-type is not going to be encoded but instead
        just passed through
        """
        if not encoding:
            encoding = self.encoding or 'utf-8'

        if isinstance(s, unicode):
            return s.encode(encoding)
        else:
            # leave it alone
            return s

16059:f5b6046f6ce8

            self._parentids[version] = parents

        return commit(parents=parents,
                date='%d %d' % (rev.timestamp, -rev.timezone),
                author=self.recode(rev.committer),
                desc=self.recode(rev.message),
                rev=version)

    def gettags(self):
        if not self.branch.supports_tags():

                # no futher changes, go to the next change
                continue

            # we got unicode paths, need to convert them
            path, topath = paths
            if path is not None:
                path = self.recode(path)
            if topath is not None:
                topath = self.recode(topath)
            seen.add(path or topath)

            if topath is None:
                # file deleted
                changes.append((path, revid))

        <http://bazaar-vcs.org/GhostRevision>
        """
        parentmap = self.sourcerepo.get_parent_map(ids)
        parents = tuple([parent for parent in ids if parent in parentmap])
        return parents