Mercurial > hg
view hgext/convert/bzr.py @ 8047:04c62275cbc7
convert: better mapfile parsing errors (issue1581/1)
author | Patrick Mezard <pmezard@gmail.com> |
---|---|
date | Sat, 11 Apr 2009 21:15:27 +0200 |
parents | f3ef8a352d83 |
children | 17ab4dab50a6 |
line wrap: on
line source
# bzr support for the convert extension # This module is for handling 'bzr', that was formerly known as Bazaar-NG; # it cannot access 'bar' repositories, but they were never used very much import os from mercurial import demandimport # these do not work with demandimport, blacklist demandimport.ignore.extend([ 'bzrlib.transactions', 'bzrlib.urlutils', ]) from mercurial.i18n import _ from mercurial import util from common import NoRepo, commit, converter_source try: # bazaar imports from bzrlib import branch, revision, errors from bzrlib.revisionspec import RevisionSpec except ImportError: pass supportedkinds = ('file', 'symlink') class bzr_source(converter_source): """Reads Bazaar repositories by using the Bazaar Python libraries""" def __init__(self, ui, path, rev=None): super(bzr_source, self).__init__(ui, path, rev=rev) if not os.path.exists(os.path.join(path, '.bzr')): raise NoRepo('%s does not look like a Bazaar repo' % path) try: # access bzrlib stuff branch except NameError: raise NoRepo('Bazaar modules could not be loaded') path = os.path.abspath(path) self.branch = branch.Branch.open(path) self.sourcerepo = self.branch.repository self._parentids = {} def before(self): """Before the conversion begins, acquire a read lock for all the operations that might need it. Fortunately read locks don't block other reads or writes to the repository, so this shouldn't have any impact on the usage of the source repository. The alternative would be locking on every operation that needs locks (there are currently two: getting the file and getting the parent map) and releasing immediately after, but this approach can take even 40% longer.""" self.sourcerepo.lock_read() def after(self): self.sourcerepo.unlock() def getheads(self): if not self.rev: return [self.branch.last_revision()] try: r = RevisionSpec.from_string(self.rev) info = r.in_history(self.branch) except errors.BzrError: raise util.Abort(_('%s is not a valid revision in current branch') % self.rev) return [info.rev_id] def getfile(self, name, rev): revtree = self.sourcerepo.revision_tree(rev) fileid = revtree.path2id(name) if fileid is None or revtree.kind(fileid) not in supportedkinds: # the file is not available anymore - was deleted raise IOError(_('%s is not available in %s anymore') % (name, rev)) sio = revtree.get_file(fileid) return sio.read() def getmode(self, name, rev): return self._modecache[(name, rev)] def getchanges(self, version): # set up caches: modecache and revtree self._modecache = {} self._revtree = self.sourcerepo.revision_tree(version) # get the parentids from the cache parentids = self._parentids.pop(version) # only diff against first parent id prevtree = self.sourcerepo.revision_tree(parentids[0]) return self._gettreechanges(self._revtree, prevtree) def getcommit(self, version): rev = self.sourcerepo.get_revision(version) # populate parent id cache if not rev.parent_ids: parents = [] self._parentids[version] = (revision.NULL_REVISION,) else: parents = self._filterghosts(rev.parent_ids) self._parentids[version] = parents return commit(parents=parents, # bzr uses 1 second timezone precision date='%d %d' % (rev.timestamp, rev.timezone / 3600), 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(): return {} tagdict = self.branch.tags.get_tag_dict() bytetags = {} for name, rev in tagdict.iteritems(): bytetags[self.recode(name)] = rev return bytetags def getchangedfiles(self, rev, i): self._modecache = {} curtree = self.sourcerepo.revision_tree(rev) parentids = self._parentids.pop(rev) if i is not None: parentid = parentids[i] else: # no parent id, get the empty revision parentid = revision.NULL_REVISION prevtree = self.sourcerepo.revision_tree(parentid) changes = [e[0] for e in self._gettreechanges(curtree, prevtree)[0]] return changes def _gettreechanges(self, current, origin): revid = current._revision_id; changes = [] renames = {} for (fileid, paths, changed_content, versioned, parent, name, kind, executable) in current.iter_changes(origin): if paths[0] == u'' or paths[1] == u'': # ignore changes to tree root continue # bazaar tracks directories, mercurial does not, so # we have to rename the directory contents if kind[1] == 'directory': if None not in paths and paths[0] != paths[1]: # neither an add nor an delete - a move # rename all directory contents manually subdir = origin.inventory.path2id(paths[0]) # get all child-entries of the directory for name, entry in origin.inventory.iter_entries(subdir): # hg does not track directory renames if entry.kind == 'directory': continue frompath = self.recode(paths[0] + '/' + name) topath = self.recode(paths[1] + '/' + name) # register the files as changed changes.append((frompath, revid)) changes.append((topath, revid)) # add to mode cache mode = ((entry.executable and 'x') or (entry.kind == 'symlink' and 's') or '') self._modecache[(topath, revid)] = mode # register the change as move renames[topath] = frompath # 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] if topath is None: # file deleted changes.append((path, revid)) continue # renamed if path and path != topath: renames[topath] = path changes.append((path, revid)) # populate the mode cache kind, executable = [e[1] for e in (kind, executable)] mode = ((executable and 'x') or (kind == 'symlink' and 's') or '') self._modecache[(topath, revid)] = mode changes.append((topath, revid)) return changes, renames def _filterghosts(self, ids): """Filters out ghost revisions which hg does not support, see <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