convert: write "repository" instead of "repo"

We should strive to avoid slang in our messages to the users.

hgext/convert/bzr.py

@@ -1,261 +1,261 b''
 # bzr.py - bzr support for the convert extension
 #
 #  Copyright 2008, 2009 Marek Kubica <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # 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',
         'ElementPath',
     ])
 
 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)
+            raise NoRepo('%s does not look like a Bazaar repository' % path)
 
         try:
             # access bzrlib stuff
             branch
         except NameError:
             raise NoRepo('Bazaar modules could not be loaded')
 
         path = os.path.abspath(path)
         self._checkrepotype(path)
         self.branch = branch.Branch.open(path)
         self.sourcerepo = self.branch.repository
         self._parentids = {}
 
     def _checkrepotype(self, path):
         # Lightweight checkouts detection is informational but probably
         # fragile at API level. It should not terminate the conversion.
         try:
             from bzrlib import bzrdir
             dir = bzrdir.BzrDir.open_containing(path)[0]
             try:
                 tree = dir.open_workingtree(recommend_upgrade=False)
                 branch = tree.branch
             except (errors.NoWorkingTree, errors.NotLocalUrl), e:
                 tree = None
                 branch = dir.open_branch()
             if (tree is not None and tree.bzrdir.root_transport.base !=
                 branch.bzrdir.root_transport.base):
                 self.ui.warn(_('warning: lightweight checkouts may cause '
                                'conversion failures, try with a regular '
                                'branch instead.\n'))
         except:
             self.ui.note(_('bzr source type could not be determined\n'))
 
     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.decode(self.encoding or 'utf-8'))
         kind = None
         if fileid is not None:
             kind = revtree.kind(fileid)
         if kind not in supportedkinds:
             # the file is not available anymore - was deleted
             raise IOError(_('%s is not available in %s anymore') %
                     (name, rev))
         if kind == 'symlink':
             target = revtree.get_symlink_target(fileid)
             if target is None:
                 raise util.Abort(_('%s.%s symlink has no target')
                                  % (name, rev))
             return target
         else:
             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,
                 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():
             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)
         if i is not None:
             parentid = self._parentids[rev][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 kind[0] not in (None, 'directory'):
                     # Replacing 'something' with a directory, record it
                     # so it can be removed.
                     changes.append((self.recode(paths[0]), revid))
 
                 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 'l')
                     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

hgext/convert/darcs.py

@@ -1,167 +1,167 b''
 # darcs.py - darcs support for the convert extension
 #
 #  Copyright 2007-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from common import NoRepo, checktool, commandline, commit, converter_source
 from mercurial.i18n import _
 from mercurial import util
 import os, shutil, tempfile
 
 # The naming drift of ElementTree is fun!
 
 try:
     from xml.etree.cElementTree import ElementTree
 except ImportError:
     try:
         from xml.etree.ElementTree import ElementTree
     except ImportError:
         try:
             from elementtree.cElementTree import ElementTree
         except ImportError:
             try:
                 from elementtree.ElementTree import ElementTree
             except ImportError:
                 ElementTree = None
 
 class darcs_source(converter_source, commandline):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev=rev)
         commandline.__init__(self, ui, 'darcs')
 
         # check for _darcs, ElementTree, _darcs/inventory so that we can
         # easily skip test-convert-darcs if ElementTree is not around
         if not os.path.exists(os.path.join(path, '_darcs', 'inventories')):
-            raise NoRepo("%s does not look like a darcs repo" % path)
+            raise NoRepo("%s does not look like a darcs repository" % path)
 
         if not os.path.exists(os.path.join(path, '_darcs')):
-            raise NoRepo("%s does not look like a darcs repo" % path)
+            raise NoRepo("%s does not look like a darcs repository" % path)
 
         checktool('darcs')
         version = self.run0('--version').splitlines()[0].strip()
         if version < '2.1':
             raise util.Abort(_('darcs version 2.1 or newer needed (found %r)') %
                              version)
 
         if ElementTree is None:
             raise util.Abort(_("Python ElementTree module is not available"))
 
         self.path = os.path.realpath(path)
 
         self.lastrev = None
         self.changes = {}
         self.parents = {}
         self.tags = {}
 
     def before(self):
         self.tmppath = tempfile.mkdtemp(
             prefix='convert-' + os.path.basename(self.path) + '-')
         output, status = self.run('init', repodir=self.tmppath)
         self.checkexit(status)
 
         tree = self.xml('changes', xml_output=True, summary=True,
                         repodir=self.path)
         tagname = None
         child = None
         for elt in tree.findall('patch'):
             node = elt.get('hash')
             name = elt.findtext('name', '')
             if name.startswith('TAG '):
                 tagname = name[4:].strip()
             elif tagname is not None:
                 self.tags[tagname] = node
                 tagname = None
             self.changes[node] = elt
             self.parents[child] = [node]
             child = node
         self.parents[child] = []
 
     def after(self):
         self.ui.debug('cleaning up %s\n' % self.tmppath)
         shutil.rmtree(self.tmppath, ignore_errors=True)
 
     def xml(self, cmd, **kwargs):
         etree = ElementTree()
         fp = self._run(cmd, **kwargs)
         etree.parse(fp)
         self.checkexit(fp.close())
         return etree.getroot()
 
     def manifest(self):
         man = []
         output, status = self.run('show', 'files', no_directories=True,
                                   repodir=self.tmppath)
         self.checkexit(status)
         for line in output.split('\n'):
             path = line[2:]
             if path:
                 man.append(path)
         return man
 
     def getheads(self):
         return self.parents[None]
 
     def getcommit(self, rev):
         elt = self.changes[rev]
         date = util.strdate(elt.get('local_date'), '%a %b %d %H:%M:%S %Z %Y')
         desc = elt.findtext('name') + '\n' + elt.findtext('comment', '')
         return commit(author=elt.get('author'), date=util.datestr(date),
                       desc=desc.strip(), parents=self.parents[rev])
 
     def pull(self, rev):
         output, status = self.run('pull', self.path, all=True,
                                   match='hash %s' % rev,
                                   no_test=True, no_posthook=True,
                                   external_merge='/bin/false',
                                   repodir=self.tmppath)
         if status:
             if output.find('We have conflicts in') == -1:
                 self.checkexit(status, output)
             output, status = self.run('revert', all=True, repodir=self.tmppath)
             self.checkexit(status, output)
 
     def getchanges(self, rev):
         copies = {}
         changes = []
         man = None
         for elt in self.changes[rev].find('summary').getchildren():
             if elt.tag in ('add_directory', 'remove_directory'):
                 continue
             if elt.tag == 'move':
                 if man is None:
                     man = self.manifest()
                 source, dest = elt.get('from'), elt.get('to')
                 if source in man:
                     # File move
                     changes.append((source, rev))
                     changes.append((dest, rev))
                     copies[dest] = source
                 else:
                     # Directory move, deduce file moves from manifest
                     source = source + '/'
                     for f in man:
                         if not f.startswith(source):
                             continue
                         fdest = dest + '/' + f[len(source):]
                         changes.append((f, rev))
                         changes.append((fdest, rev))
                         copies[fdest] = f
             else:
                 changes.append((elt.text.strip(), rev))
         self.pull(rev)
         self.lastrev = rev
         return sorted(changes), copies
 
     def getfile(self, name, rev):
         if rev != self.lastrev:
             raise util.Abort(_('internal calling inconsistency'))
         return open(os.path.join(self.tmppath, name), 'rb').read()
 
     def getmode(self, name, rev):
         mode = os.lstat(os.path.join(self.tmppath, name)).st_mode
         return (mode & 0111) and 'x' or ''
 
     def gettags(self):
         return self.tags

hgext/convert/git.py

@@ -1,155 +1,155 b''
 # git.py - git support for the convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os
 from mercurial import util
 
 from common import NoRepo, commit, converter_source, checktool
 
 class convert_git(converter_source):
     # Windows does not support GIT_DIR= construct while other systems
     # cannot remove environment variable. Just assume none have
     # both issues.
     if hasattr(os, 'unsetenv'):
         def gitcmd(self, s):
             prevgitdir = os.environ.get('GIT_DIR')
             os.environ['GIT_DIR'] = self.path
             try:
                 return util.popen(s, 'rb')
             finally:
                 if prevgitdir is None:
                     del os.environ['GIT_DIR']
                 else:
                     os.environ['GIT_DIR'] = prevgitdir
     else:
         def gitcmd(self, s):
             return util.popen('GIT_DIR=%s %s' % (self.path, s), 'rb')
 
     def __init__(self, ui, path, rev=None):
         super(convert_git, self).__init__(ui, path, rev=rev)
 
         if os.path.isdir(path + "/.git"):
             path += "/.git"
         if not os.path.exists(path + "/objects"):
-            raise NoRepo("%s does not look like a Git repo" % path)
+            raise NoRepo("%s does not look like a Git repository" % path)
 
         checktool('git', 'git')
 
         self.path = path
 
     def getheads(self):
         if not self.rev:
             fh = self.gitcmd('git rev-parse --branches --remotes')
             return fh.read().splitlines()
         else:
             fh = self.gitcmd("git rev-parse --verify %s" % self.rev)
             return [fh.read()[:-1]]
 
     def catfile(self, rev, type):
         if rev == "0" * 40:
             raise IOError()
         fh = self.gitcmd("git cat-file %s %s" % (type, rev))
         return fh.read()
 
     def getfile(self, name, rev):
         return self.catfile(rev, "blob")
 
     def getmode(self, name, rev):
         return self.modecache[(name, rev)]
 
     def getchanges(self, version):
         self.modecache = {}
         fh = self.gitcmd("git diff-tree -z --root -m -r %s" % version)
         changes = []
         seen = set()
         entry = None
         for l in fh.read().split('\x00'):
             if not entry:
                 if not l.startswith(':'):
                     continue
                 entry = l
                 continue
             f = l
             if f not in seen:
                 seen.add(f)
                 entry = entry.split()
                 h = entry[3]
                 p = (entry[1] == "100755")
                 s = (entry[1] == "120000")
                 self.modecache[(f, h)] = (p and "x") or (s and "l") or ""
                 changes.append((f, h))
             entry = None
         return (changes, {})
 
     def getcommit(self, version):
         c = self.catfile(version, "commit") # read the commit hash
         end = c.find("\n\n")
         message = c[end + 2:]
         message = self.recode(message)
         l = c[:end].splitlines()
         parents = []
         author = committer = None
         for e in l[1:]:
             n, v = e.split(" ", 1)
             if n == "author":
                 p = v.split()
                 tm, tz = p[-2:]
                 author = " ".join(p[:-2])
                 if author[0] == "<": author = author[1:-1]
                 author = self.recode(author)
             if n == "committer":
                 p = v.split()
                 tm, tz = p[-2:]
                 committer = " ".join(p[:-2])
                 if committer[0] == "<": committer = committer[1:-1]
                 committer = self.recode(committer)
             if n == "parent":
                 parents.append(v)
 
         if committer and committer != author:
             message += "\ncommitter: %s\n" % committer
         tzs, tzh, tzm = tz[-5:-4] + "1", tz[-4:-2], tz[-2:]
         tz = -int(tzs) * (int(tzh) * 3600 + int(tzm))
         date = tm + " " + str(tz)
 
         c = commit(parents=parents, date=date, author=author, desc=message,
                    rev=version)
         return c
 
     def gettags(self):
         tags = {}
         fh = self.gitcmd('git ls-remote --tags "%s"' % self.path)
         prefix = 'refs/tags/'
         for line in fh:
             line = line.strip()
             if not line.endswith("^{}"):
                 continue
             node, tag = line.split(None, 1)
             if not tag.startswith(prefix):
                 continue
             tag = tag[len(prefix):-3]
             tags[tag] = node
 
         return tags
 
     def getchangedfiles(self, version, i):
         changes = []
         if i is None:
             fh = self.gitcmd("git diff-tree --root -m -r %s" % version)
             for l in fh:
                 if "\t" not in l:
                     continue
                 m, f = l[:-1].split("\t")
                 changes.append(f)
             fh.close()
         else:
             fh = self.gitcmd('git diff-tree --name-only --root -r %s "%s^%s" --'
                              % (version, version, i + 1))
             changes = [f.rstrip('\n') for f in fh]
             fh.close()
 
         return changes

hgext/convert/gnuarch.py

@@ -1,345 +1,346 b''
 # gnuarch.py - GNU Arch support for the convert extension
 #
 #  Copyright 2008, 2009 Aleix Conchillo Flaque <[e-mail]>
 #  and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from common import NoRepo, commandline, commit, converter_source
 from mercurial.i18n import _
 from mercurial import util
 import os, shutil, tempfile, stat, locale
 from email.Parser import Parser
 
 class gnuarch_source(converter_source, commandline):
 
     class gnuarch_rev(object):
         def __init__(self, rev):
             self.rev = rev
             self.summary = ''
             self.date = None
             self.author = ''
             self.continuationof = None
             self.add_files = []
             self.mod_files = []
             self.del_files = []
             self.ren_files = {}
             self.ren_dirs = {}
 
     def __init__(self, ui, path, rev=None):
         super(gnuarch_source, self).__init__(ui, path, rev=rev)
 
         if not os.path.exists(os.path.join(path, '{arch}')):
-            raise NoRepo(_("%s does not look like a GNU Arch repo") % path)
+            raise NoRepo(_("%s does not look like a GNU Arch repository")
+                         % path)
 
         # Could use checktool, but we want to check for baz or tla.
         self.execmd = None
         if util.find_exe('baz'):
             self.execmd = 'baz'
         else:
             if util.find_exe('tla'):
                 self.execmd = 'tla'
             else:
                 raise util.Abort(_('cannot find a GNU Arch tool'))
 
         commandline.__init__(self, ui, self.execmd)
 
         self.path = os.path.realpath(path)
         self.tmppath = None
 
         self.treeversion = None
         self.lastrev = None
         self.changes = {}
         self.parents = {}
         self.tags = {}
         self.modecache = {}
         self.catlogparser = Parser()
         self.locale = locale.getpreferredencoding()
         self.archives = []
 
     def before(self):
         # Get registered archives
         self.archives = [i.rstrip('\n')
                          for i in self.runlines0('archives', '-n')]
 
         if self.execmd == 'tla':
             output = self.run0('tree-version', self.path)
         else:
             output = self.run0('tree-version', '-d', self.path)
         self.treeversion = output.strip()
 
         # Get name of temporary directory
         version = self.treeversion.split('/')
         self.tmppath = os.path.join(tempfile.gettempdir(),
                                     'hg-%s' % version[1])
 
         # Generate parents dictionary
         self.parents[None] = []
         treeversion = self.treeversion
         child = None
         while treeversion:
             self.ui.status(_('analyzing tree version %s...\n') % treeversion)
 
             archive = treeversion.split('/')[0]
             if archive not in self.archives:
                 self.ui.status(_('tree analysis stopped because it points to '
                                  'an unregistered archive %s...\n') % archive)
                 break
 
             # Get the complete list of revisions for that tree version
             output, status = self.runlines('revisions', '-r', '-f', treeversion)
             self.checkexit(status, 'failed retrieveing revisions for %s'
                            % treeversion)
 
             # No new iteration unless a revision has a continuation-of header
             treeversion = None
 
             for l in output:
                 rev = l.strip()
                 self.changes[rev] = self.gnuarch_rev(rev)
                 self.parents[rev] = []
 
                 # Read author, date and summary
                 catlog, status = self.run('cat-log', '-d', self.path, rev)
                 if status:
                     catlog  = self.run0('cat-archive-log', rev)
                 self._parsecatlog(catlog, rev)
 
                 # Populate the parents map
                 self.parents[child].append(rev)
 
                 # Keep track of the current revision as the child of the next
                 # revision scanned
                 child = rev
 
                 # Check if we have to follow the usual incremental history
                 # or if we have to 'jump' to a different treeversion given
                 # by the continuation-of header.
                 if self.changes[rev].continuationof:
                     treeversion = '--'.join(
                         self.changes[rev].continuationof.split('--')[:-1])
                     break
 
                 # If we reached a base-0 revision w/o any continuation-of
                 # header, it means the tree history ends here.
                 if rev[-6:] == 'base-0':
                     break
 
     def after(self):
         self.ui.debug('cleaning up %s\n' % self.tmppath)
         shutil.rmtree(self.tmppath, ignore_errors=True)
 
     def getheads(self):
         return self.parents[None]
 
     def getfile(self, name, rev):
         if rev != self.lastrev:
             raise util.Abort(_('internal calling inconsistency'))
 
         # Raise IOError if necessary (i.e. deleted files).
         if not os.path.exists(os.path.join(self.tmppath, name)):
             raise IOError
 
         data, mode = self._getfile(name, rev)
         self.modecache[(name, rev)] = mode
 
         return data
 
     def getmode(self, name, rev):
         return self.modecache[(name, rev)]
 
     def getchanges(self, rev):
         self.modecache = {}
         self._update(rev)
         changes = []
         copies = {}
 
         for f in self.changes[rev].add_files:
             changes.append((f, rev))
 
         for f in self.changes[rev].mod_files:
             changes.append((f, rev))
 
         for f in self.changes[rev].del_files:
             changes.append((f, rev))
 
         for src in self.changes[rev].ren_files:
             to = self.changes[rev].ren_files[src]
             changes.append((src, rev))
             changes.append((to, rev))
             copies[to] = src
 
         for src in self.changes[rev].ren_dirs:
             to = self.changes[rev].ren_dirs[src]
             chgs, cps = self._rendirchanges(src, to)
             changes += [(f, rev) for f in chgs]
             copies.update(cps)
 
         self.lastrev = rev
         return sorted(set(changes)), copies
 
     def getcommit(self, rev):
         changes = self.changes[rev]
         return commit(author=changes.author, date=changes.date,
                       desc=changes.summary, parents=self.parents[rev], rev=rev)
 
     def gettags(self):
         return self.tags
 
     def _execute(self, cmd, *args, **kwargs):
         cmdline = [self.execmd, cmd]
         cmdline += args
         cmdline = [util.shellquote(arg) for arg in cmdline]
         cmdline += ['>', util.nulldev, '2>', util.nulldev]
         cmdline = util.quotecommand(' '.join(cmdline))
         self.ui.debug(cmdline, '\n')
         return os.system(cmdline)
 
     def _update(self, rev):
         self.ui.debug('applying revision %s...\n' % rev)
         changeset, status = self.runlines('replay', '-d', self.tmppath,
                                               rev)
         if status:
             # Something went wrong while merging (baz or tla
             # issue?), get latest revision and try from there
             shutil.rmtree(self.tmppath, ignore_errors=True)
             self._obtainrevision(rev)
         else:
             old_rev = self.parents[rev][0]
             self.ui.debug('computing changeset between %s and %s...\n'
                           % (old_rev, rev))
             self._parsechangeset(changeset, rev)
 
     def _getfile(self, name, rev):
         mode = os.lstat(os.path.join(self.tmppath, name)).st_mode
         if stat.S_ISLNK(mode):
             data = os.readlink(os.path.join(self.tmppath, name))
             mode = mode and 'l' or ''
         else:
             data = open(os.path.join(self.tmppath, name), 'rb').read()
             mode = (mode & 0111) and 'x' or ''
         return data, mode
 
     def _exclude(self, name):
         exclude = ['{arch}', '.arch-ids', '.arch-inventory']
         for exc in exclude:
             if name.find(exc) != -1:
                 return True
         return False
 
     def _readcontents(self, path):
         files = []
         contents = os.listdir(path)
         while len(contents) > 0:
             c = contents.pop()
             p = os.path.join(path, c)
             # os.walk could be used, but here we avoid internal GNU
             # Arch files and directories, thus saving a lot time.
             if not self._exclude(p):
                 if os.path.isdir(p):
                     contents += [os.path.join(c, f) for f in os.listdir(p)]
                 else:
                     files.append(c)
         return files
 
     def _rendirchanges(self, src, dest):
         changes = []
         copies = {}
         files = self._readcontents(os.path.join(self.tmppath, dest))
         for f in files:
             s = os.path.join(src, f)
             d = os.path.join(dest, f)
             changes.append(s)
             changes.append(d)
             copies[d] = s
         return changes, copies
 
     def _obtainrevision(self, rev):
         self.ui.debug('obtaining revision %s...\n' % rev)
         output = self._execute('get', rev, self.tmppath)
         self.checkexit(output)
         self.ui.debug('analyzing revision %s...\n' % rev)
         files = self._readcontents(self.tmppath)
         self.changes[rev].add_files += files
 
     def _stripbasepath(self, path):
         if path.startswith('./'):
             return path[2:]
         return path
 
     def _parsecatlog(self, data, rev):
         try:
             catlog = self.catlogparser.parsestr(data)
 
             # Commit date
             self.changes[rev].date = util.datestr(
                 util.strdate(catlog['Standard-date'],
                              '%Y-%m-%d %H:%M:%S'))
 
             # Commit author
             self.changes[rev].author = self.recode(catlog['Creator'])
 
             # Commit description
             self.changes[rev].summary = '\n\n'.join((catlog['Summary'],
                                                     catlog.get_payload()))
             self.changes[rev].summary = self.recode(self.changes[rev].summary)
 
             # Commit revision origin when dealing with a branch or tag
             if 'Continuation-of' in catlog:
                 self.changes[rev].continuationof = self.recode(
                     catlog['Continuation-of'])
         except Exception:
             raise util.Abort(_('could not parse cat-log of %s') % rev)
 
     def _parsechangeset(self, data, rev):
         for l in data:
             l = l.strip()
             # Added file (ignore added directory)
             if l.startswith('A') and not l.startswith('A/'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].add_files.append(file)
             # Deleted file (ignore deleted directory)
             elif l.startswith('D') and not l.startswith('D/'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].del_files.append(file)
             # Modified binary file
             elif l.startswith('Mb'):
                 file = self._stripbasepath(l[2:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Modified link
             elif l.startswith('M->'):
                 file = self._stripbasepath(l[3:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Modified file
             elif l.startswith('M'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Renamed file (or link)
             elif l.startswith('=>'):
                 files = l[2:].strip().split(' ')
                 if len(files) == 1:
                     files = l[2:].strip().split('\t')
                 src = self._stripbasepath(files[0])
                 dst = self._stripbasepath(files[1])
                 if not self._exclude(src) and not self._exclude(dst):
                     self.changes[rev].ren_files[src] = dst
             # Conversion from file to link or from link to file (modified)
             elif l.startswith('ch'):
                 file = self._stripbasepath(l[2:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Renamed directory
             elif l.startswith('/>'):
                 dirs = l[2:].strip().split(' ')
                 if len(dirs) == 1:
                     dirs = l[2:].strip().split('\t')
                 src = self._stripbasepath(dirs[0])
                 dst = self._stripbasepath(dirs[1])
                 if not self._exclude(src) and not self._exclude(dst):
                     self.changes[rev].ren_dirs[src] = dst

hgext/convert/hg.py

@@ -1,374 +1,377 b''
 # hg.py - hg backend for convert extension
 #
 #  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 # Notes 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.
 #
 # * Using "--config convert.hg.saverev=true" will make the source
 #   identifier to be stored in the converted revision. This will cause
 #   the converted revision to have a different identity than the
 #   source.
 
 
 import os, time, cStringIO
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import hg, util, context, error
 
 from common import NoRepo, commit, converter_source, converter_sink
 
 class mercurial_sink(converter_sink):
     def __init__(self, ui, path):
         converter_sink.__init__(self, ui, path)
         self.branchnames = ui.configbool('convert', 'hg.usebranchnames', True)
         self.clonebranches = ui.configbool('convert', 'hg.clonebranches', False)
         self.tagsbranch = ui.config('convert', 'hg.tagsbranch', 'default')
         self.lastbranch = None
         if os.path.isdir(path) and len(os.listdir(path)) > 0:
             try:
                 self.repo = hg.repository(self.ui, path)
                 if not self.repo.local():
-                    raise NoRepo(_('%s is not a local Mercurial repo') % path)
+                    raise NoRepo(_('%s is not a local Mercurial repository')
+                                 % path)
             except error.RepoError, err:
                 ui.traceback()
                 raise NoRepo(err.args[0])
         else:
             try:
                 ui.status(_('initializing destination %s repository\n') % path)
                 self.repo = hg.repository(self.ui, path, create=True)
                 if not self.repo.local():
-                    raise NoRepo(_('%s is not a local Mercurial repo') % path)
+                    raise NoRepo(_('%s is not a local Mercurial repository')
+                                 % path)
                 self.created.append(path)
             except error.RepoError:
                 ui.traceback()
-                raise NoRepo("could not create hg repo %s as sink" % path)
+                raise NoRepo("could not create hg repository %s as sink"
+                             % path)
         self.lock = None
         self.wlock = None
         self.filemapmode = False
 
     def before(self):
         self.ui.debug('run hg sink pre-conversion action\n')
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
 
     def after(self):
         self.ui.debug('run hg sink post-conversion action\n')
         if self.lock:
             self.lock.release()
         if self.wlock:
             self.wlock.release()
 
     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 setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
 
         setbranch = (branch != self.lastbranch)
         self.lastbranch = branch
         if not branch:
             branch = 'default'
         pbranches = [(b[0], b[1] and b[1] or 'default') for b in pbranches]
         pbranch = pbranches and pbranches[0][1] or 'default'
 
         branchpath = os.path.join(self.path, branch)
         if setbranch:
             self.after()
             try:
                 self.repo = hg.repository(self.ui, branchpath)
             except:
                 self.repo = hg.repository(self.ui, branchpath, create=True)
             self.before()
 
         # pbranches may bring revisions from other branches (merge parents)
         # Make sure we have them, or pull them.
         missings = {}
         for b in pbranches:
             try:
                 self.repo.lookup(b[0])
             except:
                 missings.setdefault(b[1], []).append(b[0])
 
         if missings:
             self.after()
             for pbranch, heads in missings.iteritems():
                 pbranchpath = os.path.join(self.path, pbranch)
                 prepo = hg.repository(self.ui, pbranchpath)
                 self.ui.note(_('pulling from %s into %s\n') % (pbranch, branch))
                 self.repo.pull(prepo, [prepo.lookup(h) for h in heads])
             self.before()
 
     def _rewritetags(self, source, revmap, data):
         fp = cStringIO.StringIO()
         for line in data.splitlines():
             s = line.split(' ', 1)
             if len(s) != 2:
                 continue
             revid = revmap.get(source.lookuprev(s[0]))
             if not revid:
                 continue
             fp.write('%s %s\n' % (revid, s[1]))
         return fp.getvalue()
 
     def putcommit(self, files, copies, parents, commit, source, revmap):
 
         files = dict(files)
         def getfilectx(repo, memctx, f):
             v = files[f]
             data = source.getfile(f, v)
             e = source.getmode(f, v)
             if f == '.hgtags':
                 data = self._rewritetags(source, revmap, data)
             return context.memfilectx(f, data, 'l' in e, 'x' in e, copies.get(f))
 
         pl = []
         for p in parents:
             if p not in pl:
                 pl.append(p)
         parents = pl
         nparents = len(parents)
         if self.filemapmode and nparents == 1:
             m1node = self.repo.changelog.read(bin(parents[0]))[0]
             parent = parents[0]
 
         if len(parents) < 2:
             parents.append(nullid)
         if len(parents) < 2:
             parents.append(nullid)
         p2 = parents.pop(0)
 
         text = commit.desc
         extra = commit.extra.copy()
         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)
             ctx = context.memctx(self.repo, (p1, p2), text, files.keys(),
                                  getfilectx, commit.author, commit.date, extra)
             self.repo.commitctx(ctx)
             text = "(octopus merge fixup)\n"
             p2 = hex(self.repo.changelog.tip())
 
         if self.filemapmode and nparents == 1:
             man = self.repo.manifest
             mnode = self.repo.changelog.read(bin(p2))[0]
             if not man.cmp(m1node, man.revision(mnode)):
                 self.ui.status(_("filtering out empty revision\n"))
                 self.repo.rollback()
                 return parent
         return p2
 
     def puttags(self, tags):
         try:
             parentctx = self.repo[self.tagsbranch]
             tagparent = parentctx.node()
         except error.RepoError:
             parentctx = None
             tagparent = nullid
 
         try:
             oldlines = sorted(parentctx['.hgtags'].data().splitlines(True))
         except:
             oldlines = []
 
         newlines = sorted([("%s %s\n" % (tags[tag], tag)) for tag in tags])
         if newlines == oldlines:
             return None, None
         data = "".join(newlines)
         def getfilectx(repo, memctx, f):
             return context.memfilectx(f, data, False, False, None)
 
         self.ui.status(_("updating tags\n"))
         date = "%s 0" % int(time.mktime(time.gmtime()))
         extra = {'branch': self.tagsbranch}
         ctx = context.memctx(self.repo, (tagparent, None), "update tags",
                              [".hgtags"], getfilectx, "convert-repo", date,
                              extra)
         self.repo.commitctx(ctx)
         return hex(self.repo.changelog.tip()), hex(tagparent)
 
     def setfilemapmode(self, active):
         self.filemapmode = active
 
 class mercurial_source(converter_source):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev)
         self.ignoreerrors = ui.configbool('convert', 'hg.ignoreerrors', False)
         self.ignored = set()
         self.saverev = ui.configbool('convert', 'hg.saverev', False)
         try:
             self.repo = hg.repository(self.ui, path)
             # try to provoke an exception if this isn't really a hg
             # repo, but some other bogus compatible-looking url
             if not self.repo.local():
                 raise error.RepoError()
         except error.RepoError:
             ui.traceback()
-            raise NoRepo("%s is not a local Mercurial repo" % path)
+            raise NoRepo("%s is not a local Mercurial repository" % path)
         self.lastrev = None
         self.lastctx = None
         self._changescache = None
         self.convertfp = None
         # Restrict converted revisions to startrev descendants
         startnode = ui.config('convert', 'hg.startrev')
         if startnode is not None:
             try:
                 startnode = self.repo.lookup(startnode)
             except error.RepoError:
                 raise util.Abort(_('%s is not a valid start revision')
                                  % startnode)
             startrev = self.repo.changelog.rev(startnode)
             children = {startnode: 1}
             for rev in self.repo.changelog.descendants(startrev):
                 children[self.repo.changelog.node(rev)] = 1
             self.keep = children.__contains__
         else:
             self.keep = util.always
 
     def changectx(self, rev):
         if self.lastrev != rev:
             self.lastctx = self.repo[rev]
             self.lastrev = rev
         return self.lastctx
 
     def parents(self, ctx):
         return [p for p in ctx.parents() if p and self.keep(p.node())]
 
     def getheads(self):
         if self.rev:
             heads = [self.repo[self.rev].node()]
         else:
             heads = self.repo.heads()
         return [hex(h) for h in heads if self.keep(h)]
 
     def getfile(self, name, rev):
         try:
             return self.changectx(rev)[name].data()
         except error.LookupError, err:
             raise IOError(err)
 
     def getmode(self, name, rev):
         return self.changectx(rev).manifest().flags(name)
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents:
             files = sorted(ctx.manifest())
             if self.ignoreerrors:
                 # calling getcopies() is a simple way to detect missing
                 # revlogs and populate self.ignored
                 self.getcopies(ctx, parents, files)
             return [(f, rev) for f in files if f not in self.ignored], {}
         if self._changescache and self._changescache[0] == rev:
             m, a, r = self._changescache[1]
         else:
             m, a, r = self.repo.status(parents[0].node(), ctx.node())[:3]
         # getcopies() detects missing revlogs early, run it before
         # filtering the changes.
         copies = self.getcopies(ctx, parents, m + a)
         changes = [(name, rev) for name in m + a + r
                    if name not in self.ignored]
         return sorted(changes), copies
 
     def getcopies(self, ctx, parents, files):
         copies = {}
         for name in files:
             if name in self.ignored:
                 continue
             try:
                 copysource, copynode = ctx.filectx(name).renamed()
                 if copysource in self.ignored or not self.keep(copynode):
                     continue
                 # Ignore copy sources not in parent revisions
                 found = False
                 for p in parents:
                     if copysource in p:
                         found = True
                         break
                 if not found:
                     continue
                 copies[name] = copysource
             except TypeError:
                 pass
             except error.LookupError, e:
                 if not self.ignoreerrors:
                     raise
                 self.ignored.add(name)
                 self.ui.warn(_('ignoring: %s\n') % e)
         return copies
 
     def getcommit(self, rev):
         ctx = self.changectx(rev)
         parents = [p.hex() for p in self.parents(ctx)]
         if self.saverev:
             crev = rev
         else:
             crev = None
         return commit(author=ctx.user(), date=util.datestr(ctx.date()),
                       desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra(),
                       sortkey=ctx.rev())
 
     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
                      if self.keep(node)])
 
     def getchangedfiles(self, rev, i):
         ctx = self.changectx(rev)
         parents = self.parents(ctx)
         if not parents and i is None:
             i = 0
             changes = [], ctx.manifest().keys(), []
         else:
             i = i or 0
             changes = self.repo.status(parents[i].node(), ctx.node())[:3]
         changes = [[f for f in l if f not in self.ignored] for l in changes]
 
         if i == 0:
             self._changescache = (rev, changes)
 
         return changes[0] + changes[1] + changes[2]
 
     def converted(self, rev, destrev):
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.path, '.hg', 'shamap'),
                                   'a')
         self.convertfp.write('%s %s\n' % (destrev, rev))
         self.convertfp.flush()
 
     def before(self):
         self.ui.debug('run hg source pre-conversion action\n')
 
     def after(self):
         self.ui.debug('run hg source post-conversion action\n')
 
     def hasnativeorder(self):
         return True
 
     def lookuprev(self, rev):
         try:
             return hex(self.repo.lookup(rev))
         except error.RepoError:
             return None

hgext/convert/monotone.py

@@ -1,228 +1,229 b''
 # monotone.py - monotone support for the convert extension
 #
 #  Copyright 2008, 2009 Mikkel Fahnoe Jorgensen <[e-mail]> and
 #  others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os, re
 from mercurial import util
 from common import NoRepo, commit, converter_source, checktool
 from common import commandline
 from mercurial.i18n import _
 
 class monotone_source(converter_source, commandline):
     def __init__(self, ui, path=None, rev=None):
         converter_source.__init__(self, ui, path, rev)
         commandline.__init__(self, ui, 'mtn')
 
         self.ui = ui
         self.path = path
 
-        norepo = NoRepo (_("%s does not look like a monotone repo") % path)
+        norepo = NoRepo(_("%s does not look like a monotone repository")
+                        % path)
         if not os.path.exists(os.path.join(path, '_MTN')):
             # Could be a monotone repository (SQLite db file)
             try:
                 header = file(path, 'rb').read(16)
             except:
                 header = ''
             if header != 'SQLite format 3\x00':
                 raise norepo
 
         # regular expressions for parsing monotone output
         space    = r'\s*'
         name     = r'\s+"((?:\\"|[^"])*)"\s*'
         value    = name
         revision = r'\s+\[(\w+)\]\s*'
         lines    = r'(?:.|\n)+'
 
         self.dir_re      = re.compile(space + "dir" + name)
         self.file_re     = re.compile(space + "file" + name +
                                       "content" + revision)
         self.add_file_re = re.compile(space + "add_file" + name +
                                       "content" + revision)
         self.patch_re    = re.compile(space + "patch" + name +
                                       "from" + revision + "to" + revision)
         self.rename_re   = re.compile(space + "rename" + name + "to" + name)
         self.delete_re   = re.compile(space + "delete" + name)
         self.tag_re      = re.compile(space + "tag" + name + "revision" +
                                       revision)
         self.cert_re     = re.compile(lines + space + "name" + name +
                                       "value" + value)
 
         attr = space + "file" + lines + space + "attr" + space
         self.attr_execute_re = re.compile(attr  + '"mtn:execute"' +
                                           space + '"true"')
 
         # cached data
         self.manifest_rev = None
         self.manifest = None
         self.files = None
         self.dirs  = None
 
         checktool('mtn', abort=False)
 
         # test if there are any revisions
         self.rev = None
         try:
             self.getheads()
         except:
             raise norepo
         self.rev = rev
 
     def mtnrun(self, *args, **kwargs):
         kwargs['d'] = self.path
         return self.run0('automate', *args, **kwargs)
 
     def mtnloadmanifest(self, rev):
         if self.manifest_rev == rev:
             return
         self.manifest = self.mtnrun("get_manifest_of", rev).split("\n\n")
         self.manifest_rev = rev
         self.files = {}
         self.dirs = {}
 
         for e in self.manifest:
             m = self.file_re.match(e)
             if m:
                 attr = ""
                 name = m.group(1)
                 node = m.group(2)
                 if self.attr_execute_re.match(e):
                     attr += "x"
                 self.files[name] = (node, attr)
             m = self.dir_re.match(e)
             if m:
                 self.dirs[m.group(1)] = True
 
     def mtnisfile(self, name, rev):
         # a non-file could be a directory or a deleted or renamed file
         self.mtnloadmanifest(rev)
         return name in self.files
 
     def mtnisdir(self, name, rev):
         self.mtnloadmanifest(rev)
         return name in self.dirs
 
     def mtngetcerts(self, rev):
         certs = {"author":"<missing>", "date":"<missing>",
             "changelog":"<missing>", "branch":"<missing>"}
         certlist = self.mtnrun("certs", rev)
         # mtn < 0.45:
         #   key "[e-mail]"
         # mtn >= 0.45:
         #   key [ff58a7ffb771907c4ff68995eada1c4da068d328]
         certlist = re.split('\n\n      key ["\[]', certlist)
         for e in certlist:
             m = self.cert_re.match(e)
             if m:
                 name, value = m.groups()
                 value = value.replace(r'\"', '"')
                 value = value.replace(r'\\', '\\')
                 certs[name] = value
         # Monotone may have subsecond dates: 2005-02-05T09:39:12.364306
         # and all times are stored in UTC
         certs["date"] = certs["date"].split('.')[0] + " UTC"
         return certs
 
     # implement the converter_source interface:
 
     def getheads(self):
         if not self.rev:
             return self.mtnrun("leaves").splitlines()
         else:
             return [self.rev]
 
     def getchanges(self, rev):
         #revision = self.mtncmd("get_revision %s" % rev).split("\n\n")
         revision = self.mtnrun("get_revision", rev).split("\n\n")
         files = {}
         ignoremove = {}
         renameddirs = []
         copies = {}
         for e in revision:
             m = self.add_file_re.match(e)
             if m:
                 files[m.group(1)] = rev
                 ignoremove[m.group(1)] = rev
             m = self.patch_re.match(e)
             if m:
                 files[m.group(1)] = rev
             # Delete/rename is handled later when the convert engine
             # discovers an IOError exception from getfile,
             # but only if we add the "from" file to the list of changes.
             m = self.delete_re.match(e)
             if m:
                 files[m.group(1)] = rev
             m = self.rename_re.match(e)
             if m:
                 toname = m.group(2)
                 fromname = m.group(1)
                 if self.mtnisfile(toname, rev):
                     ignoremove[toname] = 1
                     copies[toname] = fromname
                     files[toname] = rev
                     files[fromname] = rev
                 elif self.mtnisdir(toname, rev):
                     renameddirs.append((fromname, toname))
 
         # Directory renames can be handled only once we have recorded
         # all new files
         for fromdir, todir in renameddirs:
             renamed = {}
             for tofile in self.files:
                 if tofile in ignoremove:
                     continue
                 if tofile.startswith(todir + '/'):
                     renamed[tofile] = fromdir + tofile[len(todir):]
                     # Avoid chained moves like:
                     # d1(/a) => d3/d1(/a)
                     # d2 => d3
                     ignoremove[tofile] = 1
             for tofile, fromfile in renamed.items():
                 self.ui.debug (_("copying file in renamed directory "
                                  "from '%s' to '%s'")
                                % (fromfile, tofile), '\n')
                 files[tofile] = rev
                 copies[tofile] = fromfile
             for fromfile in renamed.values():
                 files[fromfile] = rev
 
         return (files.items(), copies)
 
     def getmode(self, name, rev):
         self.mtnloadmanifest(rev)
         node, attr = self.files.get(name, (None, ""))
         return attr
 
     def getfile(self, name, rev):
         if not self.mtnisfile(name, rev):
             raise IOError() # file was deleted or renamed
         try:
             return self.mtnrun("get_file_of", name, r=rev)
         except:
             raise IOError() # file was deleted or renamed
 
     def getcommit(self, rev):
         certs   = self.mtngetcerts(rev)
         return commit(
             author=certs["author"],
             date=util.datestr(util.strdate(certs["date"], "%Y-%m-%dT%H:%M:%S")),
             desc=certs["changelog"],
             rev=rev,
             parents=self.mtnrun("parents", rev).splitlines(),
             branch=certs["branch"])
 
     def gettags(self):
         tags = {}
         for e in self.mtnrun("tags").split("\n\n"):
             m = self.tag_re.match(e)
             if m:
                 tags[m.group(1)] = m.group(2)
         return tags
 
     def getchangedfiles(self, rev, i):
         # This function is only needed to support --filemap
         # ... and we don't support that
         raise NotImplementedError()

hgext/convert/p4.py

@@ -1,208 +1,208 b''
 # Perforce source for convert extension.
 #
 # Copyright 2009, Frank Kingswood <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from mercurial import util
 from mercurial.i18n import _
 
 from common import commit, converter_source, checktool, NoRepo
 import marshal
 import re
 
 def loaditer(f):
     "Yield the dictionary objects generated by p4"
     try:
         while True:
             d = marshal.load(f)
             if not d:
                 break
             yield d
     except EOFError:
         pass
 
 class p4_source(converter_source):
     def __init__(self, ui, path, rev=None):
         super(p4_source, self).__init__(ui, path, rev=rev)
 
         if "/" in path and not path.startswith('//'):
-            raise NoRepo('%s does not look like a P4 repo' % path)
+            raise NoRepo('%s does not look like a P4 repository' % path)
 
         checktool('p4', abort=False)
 
         self.p4changes = {}
         self.heads = {}
         self.changeset = {}
         self.files = {}
         self.tags = {}
         self.lastbranch = {}
         self.parent = {}
         self.encoding = "latin_1"
         self.depotname = {}           # mapping from local name to depot name
         self.modecache = {}
         self.re_type = re.compile(
             "([a-z]+)?(text|binary|symlink|apple|resource|unicode|utf\d+)"
             "(\+\w+)?$")
         self.re_keywords = re.compile(
             r"\$(Id|Header|Date|DateTime|Change|File|Revision|Author)"
             r":[^$\n]*\$")
         self.re_keywords_old = re.compile("\$(Id|Header):[^$\n]*\$")
 
         self._parse(ui, path)
 
     def _parse_view(self, path):
         "Read changes affecting the path"
         cmd = 'p4 -G changes -s submitted "%s"' % path
         stdout = util.popen(cmd, mode='rb')
         for d in loaditer(stdout):
             c = d.get("change", None)
             if c:
                 self.p4changes[c] = True
 
     def _parse(self, ui, path):
         "Prepare list of P4 filenames and revisions to import"
         ui.status(_('reading p4 views\n'))
 
         # read client spec or view
         if "/" in path:
             self._parse_view(path)
             if path.startswith("//") and path.endswith("/..."):
                 views = {path[:-3]:""}
             else:
                 views = {"//": ""}
         else:
             cmd = 'p4 -G client -o "%s"' % path
             clientspec = marshal.load(util.popen(cmd, mode='rb'))
 
             views = {}
             for client in clientspec:
                 if client.startswith("View"):
                     sview, cview = clientspec[client].split()
                     self._parse_view(sview)
                     if sview.endswith("...") and cview.endswith("..."):
                         sview = sview[:-3]
                         cview = cview[:-3]
                     cview = cview[2:]
                     cview = cview[cview.find("/") + 1:]
                     views[sview] = cview
 
         # list of changes that affect our source files
         self.p4changes = self.p4changes.keys()
         self.p4changes.sort(key=int)
 
         # list with depot pathnames, longest first
         vieworder = views.keys()
         vieworder.sort(key=len, reverse=True)
 
         # handle revision limiting
         startrev = self.ui.config('convert', 'p4.startrev', default=0)
         self.p4changes = [x for x in self.p4changes
                           if ((not startrev or int(x) >= int(startrev)) and
                               (not self.rev or int(x) <= int(self.rev)))]
 
         # now read the full changelists to get the list of file revisions
         ui.status(_('collecting p4 changelists\n'))
         lastid = None
         for change in self.p4changes:
             cmd = "p4 -G describe %s" % change
             stdout = util.popen(cmd, mode='rb')
             d = marshal.load(stdout)
 
             desc = self.recode(d["desc"])
             shortdesc = desc.split("\n", 1)[0]
             t = '%s %s' % (d["change"], repr(shortdesc)[1:-1])
             ui.status(util.ellipsis(t, 80) + '\n')
 
             if lastid:
                 parents = [lastid]
             else:
                 parents = []
 
             date = (int(d["time"]), 0)     # timezone not set
             c = commit(author=self.recode(d["user"]), date=util.datestr(date),
                        parents=parents, desc=desc, branch='',
                        extra={"p4": change})
 
             files = []
             i = 0
             while ("depotFile%d" % i) in d and ("rev%d" % i) in d:
                 oldname = d["depotFile%d" % i]
                 filename = None
                 for v in vieworder:
                     if oldname.startswith(v):
                         filename = views[v] + oldname[len(v):]
                         break
                 if filename:
                     files.append((filename, d["rev%d" % i]))
                     self.depotname[filename] = oldname
                 i += 1
             self.changeset[change] = c
             self.files[change] = files
             lastid = change
 
         if lastid:
             self.heads = [lastid]
 
     def getheads(self):
         return self.heads
 
     def getfile(self, name, rev):
         cmd = 'p4 -G print "%s#%s"' % (self.depotname[name], rev)
         stdout = util.popen(cmd, mode='rb')
 
         mode = None
         contents = ""
         keywords = None
 
         for d in loaditer(stdout):
             code = d["code"]
             data = d.get("data")
 
             if code == "error":
                 raise IOError(d["generic"], data)
 
             elif code == "stat":
                 p4type = self.re_type.match(d["type"])
                 if p4type:
                     mode = ""
                     flags = (p4type.group(1) or "") + (p4type.group(3) or "")
                     if "x" in flags:
                         mode = "x"
                     if p4type.group(2) == "symlink":
                         mode = "l"
                     if "ko" in flags:
                         keywords = self.re_keywords_old
                     elif "k" in flags:
                         keywords = self.re_keywords
 
             elif code == "text" or code == "binary":
                 contents += data
 
         if mode is None:
             raise IOError(0, "bad stat")
 
         self.modecache[(name, rev)] = mode
 
         if keywords:
             contents = keywords.sub("$\\1$", contents)
         if mode == "l" and contents.endswith("\n"):
             contents = contents[:-1]
 
         return contents
 
     def getmode(self, name, rev):
         return self.modecache[(name, rev)]
 
     def getchanges(self, rev):
         return self.files[rev], {}
 
     def getcommit(self, rev):
         return self.changeset[rev]
 
     def gettags(self):
         return self.tags
 
     def getchangedfiles(self, rev, i):
         return sorted([x[0] for x in self.files[rev]])

hgext/convert/subversion.py

@@ -1,1171 +1,1172 b''
 # Subversion 1.4/1.5 Python API backend
 #
 # Copyright(C) 2007 Daniel Holth et al
 
 import os
 import re
 import sys
 import cPickle as pickle
 import tempfile
 import urllib
 import urllib2
 
 from mercurial import strutil, util, encoding
 from mercurial.i18n import _
 
 # Subversion stuff. Works best with very recent Python SVN bindings
 # e.g. SVN 1.5 or backports. Thanks to the bzr folks for enhancing
 # these bindings.
 
 from cStringIO import StringIO
 
 from common import NoRepo, MissingTool, commit, encodeargs, decodeargs
 from common import commandline, converter_source, converter_sink, mapfile
 
 try:
     from svn.core import SubversionException, Pool
     import svn
     import svn.client
     import svn.core
     import svn.ra
     import svn.delta
     import transport
     import warnings
     warnings.filterwarnings('ignore',
             module='svn.core',
             category=DeprecationWarning)
 
 except ImportError:
     pass
 
 class SvnPathNotFound(Exception):
     pass
 
 def geturl(path):
     try:
         return svn.client.url_from_path(svn.core.svn_path_canonicalize(path))
     except SubversionException:
         pass
     if os.path.isdir(path):
         path = os.path.normpath(os.path.abspath(path))
         if os.name == 'nt':
             path = '/' + util.normpath(path)
         # Module URL is later compared with the repository URL returned
         # by svn API, which is UTF-8.
         path = encoding.tolocal(path)
         return 'file://%s' % urllib.quote(path)
     return path
 
 def optrev(number):
     optrev = svn.core.svn_opt_revision_t()
     optrev.kind = svn.core.svn_opt_revision_number
     optrev.value.number = number
     return optrev
 
 class changedpath(object):
     def __init__(self, p):
         self.copyfrom_path = p.copyfrom_path
         self.copyfrom_rev = p.copyfrom_rev
         self.action = p.action
 
 def get_log_child(fp, url, paths, start, end, limit=0, discover_changed_paths=True,
                     strict_node_history=False):
     protocol = -1
     def receiver(orig_paths, revnum, author, date, message, pool):
         if orig_paths is not None:
             for k, v in orig_paths.iteritems():
                 orig_paths[k] = changedpath(v)
         pickle.dump((orig_paths, revnum, author, date, message),
                     fp, protocol)
 
     try:
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
     except SubversionException, (inst, num):
         pickle.dump(num, fp, protocol)
     except IOError:
         # Caller may interrupt the iteration
         pickle.dump(None, fp, protocol)
     else:
         pickle.dump(None, fp, protocol)
     fp.close()
     # With large history, cleanup process goes crazy and suddenly
     # consumes *huge* amount of memory. The output file being closed,
     # there is no need for clean termination.
     os._exit(0)
 
 def debugsvnlog(ui, **opts):
     """Fetch SVN log in a subprocess and channel them back to parent to
     avoid memory collection issues.
     """
     util.set_binary(sys.stdin)
     util.set_binary(sys.stdout)
     args = decodeargs(sys.stdin.read())
     get_log_child(sys.stdout, *args)
 
 class logstream(object):
     """Interruptible revision log iterator."""
     def __init__(self, stdout):
         self._stdout = stdout
 
     def __iter__(self):
         while True:
             try:
                 entry = pickle.load(self._stdout)
             except EOFError:
                 raise util.Abort(_('Mercurial failed to run itself, check'
                                    ' hg executable is in PATH'))
             try:
                 orig_paths, revnum, author, date, message = entry
             except:
                 if entry is None:
                     break
                 raise SubversionException("child raised exception", entry)
             yield entry
 
     def close(self):
         if self._stdout:
             self._stdout.close()
             self._stdout = None
 
 
 # Check to see if the given path is a local Subversion repo. Verify this by
 # looking for several svn-specific files and directories in the given
 # directory.
 def filecheck(ui, path, proto):
     for x in ('locks', 'hooks', 'format', 'db'):
         if not os.path.exists(os.path.join(path, x)):
             return False
     return True
 
 # Check to see if a given path is the root of an svn repo over http. We verify
 # this by requesting a version-controlled URL we know can't exist and looking
 # for the svn-specific "not found" XML.
 def httpcheck(ui, path, proto):
     try:
         opener = urllib2.build_opener()
         rsp = opener.open('%s://%s/!svn/ver/0/.svn' % (proto, path))
         data = rsp.read()
     except urllib2.HTTPError, inst:
         if inst.code != 404:
             # Except for 404 we cannot know for sure this is not an svn repo
             ui.warn(_('svn: cannot probe remote repository, assume it could '
                       'be a subversion repository. Use --source-type if you '
                       'know better.\n'))
             return True
         data = inst.fp.read()
     except:
         # Could be urllib2.URLError if the URL is invalid or anything else.
         return False
     return '<m:human-readable errcode="160013">' in data
 
 protomap = {'http': httpcheck,
             'https': httpcheck,
             'file': filecheck,
             }
 def issvnurl(ui, url):
     try:
         proto, path = url.split('://', 1)
         if proto == 'file':
             path = urllib.url2pathname(path)
     except ValueError:
         proto = 'file'
         path = os.path.abspath(url)
     if proto == 'file':
         path = path.replace(os.sep, '/')
     check = protomap.get(proto, lambda *args: False)
     while '/' in path:
         if check(ui, path, proto):
             return True
         path = path.rsplit('/', 1)[0]
     return False
 
 # SVN conversion code stolen from bzr-svn and tailor
 #
 # Subversion looks like a versioned filesystem, branches structures
 # are defined by conventions and not enforced by the tool. First,
 # we define the potential branches (modules) as "trunk" and "branches"
 # children directories. Revisions are then identified by their
 # module and revision number (and a repository identifier).
 #
 # The revision graph is really a tree (or a forest). By default, a
 # revision parent is the previous revision in the same module. If the
 # module directory is copied/moved from another module then the
 # revision is the module root and its parent the source revision in
 # the parent module. A revision has at most one parent.
 #
 class svn_source(converter_source):
     def __init__(self, ui, url, rev=None):
         super(svn_source, self).__init__(ui, url, rev=rev)
 
         if not (url.startswith('svn://') or url.startswith('svn+ssh://') or
                 (os.path.exists(url) and
                  os.path.exists(os.path.join(url, '.svn'))) or
                 issvnurl(ui, url)):
-            raise NoRepo("%s does not look like a Subversion repo" % url)
+            raise NoRepo("%s does not look like a Subversion repository" % url)
 
         try:
             SubversionException
         except NameError:
             raise MissingTool(_('Subversion python bindings could not be loaded'))
 
         try:
             version = svn.core.SVN_VER_MAJOR, svn.core.SVN_VER_MINOR
             if version < (1, 4):
                 raise MissingTool(_('Subversion python bindings %d.%d found, '
                                     '1.4 or later required') % version)
         except AttributeError:
             raise MissingTool(_('Subversion python bindings are too old, 1.4 '
                                 'or later required'))
 
         self.lastrevs = {}
 
         latest = None
         try:
             # Support file://path@rev syntax. Useful e.g. to convert
             # deleted branches.
             at = url.rfind('@')
             if at >= 0:
                 latest = int(url[at + 1:])
                 url = url[:at]
         except ValueError:
             pass
         self.url = geturl(url)
         self.encoding = 'UTF-8' # Subversion is always nominal UTF-8
         try:
             self.transport = transport.SvnRaTransport(url=self.url)
             self.ra = self.transport.ra
             self.ctx = self.transport.client
             self.baseurl = svn.ra.get_repos_root(self.ra)
             # Module is either empty or a repository path starting with
             # a slash and not ending with a slash.
             self.module = urllib.unquote(self.url[len(self.baseurl):])
             self.prevmodule = None
             self.rootmodule = self.module
             self.commits = {}
             self.paths = {}
             self.uuid = svn.ra.get_uuid(self.ra)
         except SubversionException:
             ui.traceback()
-            raise NoRepo("%s does not look like a Subversion repo" % self.url)
+            raise NoRepo("%s does not look like a Subversion repository"
+                         % self.url)
 
         if rev:
             try:
                 latest = int(rev)
             except ValueError:
                 raise util.Abort(_('svn: revision %s is not an integer') % rev)
 
         self.startrev = self.ui.config('convert', 'svn.startrev', default=0)
         try:
             self.startrev = int(self.startrev)
             if self.startrev < 0:
                 self.startrev = 0
         except ValueError:
             raise util.Abort(_('svn: start revision %s is not an integer')
                              % self.startrev)
 
         self.head = self.latest(self.module, latest)
         if not self.head:
             raise util.Abort(_('no revision found in module %s')
                              % self.module)
         self.last_changed = self.revnum(self.head)
 
         self._changescache = None
 
         if os.path.exists(os.path.join(url, '.svn/entries')):
             self.wc = url
         else:
             self.wc = None
         self.convertfp = None
 
     def setrevmap(self, revmap):
         lastrevs = {}
         for revid in revmap.iterkeys():
             uuid, module, revnum = self.revsplit(revid)
             lastrevnum = lastrevs.setdefault(module, revnum)
             if revnum > lastrevnum:
                 lastrevs[module] = revnum
         self.lastrevs = lastrevs
 
     def exists(self, path, optrev):
         try:
             svn.client.ls(self.url.rstrip('/') + '/' + urllib.quote(path),
                                  optrev, False, self.ctx)
             return True
         except SubversionException:
             return False
 
     def getheads(self):
 
         def isdir(path, revnum):
             kind = self._checkpath(path, revnum)
             return kind == svn.core.svn_node_dir
 
         def getcfgpath(name, rev):
             cfgpath = self.ui.config('convert', 'svn.' + name)
             if cfgpath is not None and cfgpath.strip() == '':
                 return None
             path = (cfgpath or name).strip('/')
             if not self.exists(path, rev):
                 if cfgpath:
                     raise util.Abort(_('expected %s to be at %r, but not found')
                                  % (name, path))
                 return None
             self.ui.note(_('found %s at %r\n') % (name, path))
             return path
 
         rev = optrev(self.last_changed)
         oldmodule = ''
         trunk = getcfgpath('trunk', rev)
         self.tags = getcfgpath('tags', rev)
         branches = getcfgpath('branches', rev)
 
         # If the project has a trunk or branches, we will extract heads
         # from them. We keep the project root otherwise.
         if trunk:
             oldmodule = self.module or ''
             self.module += '/' + trunk
             self.head = self.latest(self.module, self.last_changed)
             if not self.head:
                 raise util.Abort(_('no revision found in module %s')
                                  % self.module)
 
         # First head in the list is the module's head
         self.heads = [self.head]
         if self.tags is not None:
             self.tags = '%s/%s' % (oldmodule , (self.tags or 'tags'))
 
         # Check if branches bring a few more heads to the list
         if branches:
             rpath = self.url.strip('/')
             branchnames = svn.client.ls(rpath + '/' + urllib.quote(branches),
                                         rev, False, self.ctx)
             for branch in branchnames.keys():
                 module = '%s/%s/%s' % (oldmodule, branches, branch)
                 if not isdir(module, self.last_changed):
                     continue
                 brevid = self.latest(module, self.last_changed)
                 if not brevid:
                     self.ui.note(_('ignoring empty branch %s\n') % branch)
                     continue
                 self.ui.note(_('found branch %s at %d\n') %
                              (branch, self.revnum(brevid)))
                 self.heads.append(brevid)
 
         if self.startrev and self.heads:
             if len(self.heads) > 1:
                 raise util.Abort(_('svn: start revision is not supported '
                                    'with more than one branch'))
             revnum = self.revnum(self.heads[0])
             if revnum < self.startrev:
                 raise util.Abort(
                     _('svn: no revision found after start revision %d')
                                  % self.startrev)
 
         return self.heads
 
     def getfile(self, file, rev):
         data, mode = self._getfile(file, rev)
         self.modecache[(file, rev)] = mode
         return data
 
     def getmode(self, file, rev):
         return self.modecache[(file, rev)]
 
     def getchanges(self, rev):
         if self._changescache and self._changescache[0] == rev:
             return self._changescache[1]
         self._changescache = None
         self.modecache = {}
         (paths, parents) = self.paths[rev]
         if parents:
             files, copies = self.expandpaths(rev, paths, parents)
         else:
             # Perform a full checkout on roots
             uuid, module, revnum = self.revsplit(rev)
             entries = svn.client.ls(self.baseurl + urllib.quote(module),
                                     optrev(revnum), True, self.ctx)
             files = [n for n, e in entries.iteritems()
                      if e.kind == svn.core.svn_node_file]
             copies = {}
 
         files.sort()
         files = zip(files, [rev] * len(files))
 
         # caller caches the result, so free it here to release memory
         del self.paths[rev]
         return (files, copies)
 
     def getchangedfiles(self, rev, i):
         changes = self.getchanges(rev)
         self._changescache = (rev, changes)
         return [f[0] for f in changes[0]]
 
     def getcommit(self, rev):
         if rev not in self.commits:
             uuid, module, revnum = self.revsplit(rev)
             self.module = module
             self.reparent(module)
             # We assume that:
             # - requests for revisions after "stop" come from the
             # revision graph backward traversal. Cache all of them
             # down to stop, they will be used eventually.
             # - requests for revisions before "stop" come to get
             # isolated branches parents. Just fetch what is needed.
             stop = self.lastrevs.get(module, 0)
             if revnum < stop:
                 stop = revnum + 1
             self._fetch_revisions(revnum, stop)
         commit = self.commits[rev]
         # caller caches the result, so free it here to release memory
         del self.commits[rev]
         return commit
 
     def gettags(self):
         tags = {}
         if self.tags is None:
             return tags
 
         # svn tags are just a convention, project branches left in a
         # 'tags' directory. There is no other relationship than
         # ancestry, which is expensive to discover and makes them hard
         # to update incrementally.  Worse, past revisions may be
         # referenced by tags far away in the future, requiring a deep
         # history traversal on every calculation.  Current code
         # performs a single backward traversal, tracking moves within
         # the tags directory (tag renaming) and recording a new tag
         # everytime a project is copied from outside the tags
         # directory. It also lists deleted tags, this behaviour may
         # change in the future.
         pendings = []
         tagspath = self.tags
         start = svn.ra.get_latest_revnum(self.ra)
         try:
             for entry in self._getlog([self.tags], start, self.startrev):
                 origpaths, revnum, author, date, message = entry
                 copies = [(e.copyfrom_path, e.copyfrom_rev, p) for p, e
                           in origpaths.iteritems() if e.copyfrom_path]
                 # Apply moves/copies from more specific to general
                 copies.sort(reverse=True)
 
                 srctagspath = tagspath
                 if copies and copies[-1][2] == tagspath:
                     # Track tags directory moves
                     srctagspath = copies.pop()[0]
 
                 for source, sourcerev, dest in copies:
                     if not dest.startswith(tagspath + '/'):
                         continue
                     for tag in pendings:
                         if tag[0].startswith(dest):
                             tagpath = source + tag[0][len(dest):]
                             tag[:2] = [tagpath, sourcerev]
                             break
                     else:
                         pendings.append([source, sourcerev, dest])
 
                 # Filter out tags with children coming from different
                 # parts of the repository like:
                 # /tags/tag.1 (from /trunk:10)
                 # /tags/tag.1/foo (from /branches/foo:12)
                 # Here/tags/tag.1 discarded as well as its children.
                 # It happens with tools like cvs2svn. Such tags cannot
                 # be represented in mercurial.
                 addeds = dict((p, e.copyfrom_path) for p, e
                               in origpaths.iteritems()
                               if e.action == 'A' and e.copyfrom_path)
                 badroots = set()
                 for destroot in addeds:
                     for source, sourcerev, dest in pendings:
                         if (not dest.startswith(destroot + '/')
                             or source.startswith(addeds[destroot] + '/')):
                             continue
                         badroots.add(destroot)
                         break
 
                 for badroot in badroots:
                     pendings = [p for p in pendings if p[2] != badroot
                                 and not p[2].startswith(badroot + '/')]
 
                 # Tell tag renamings from tag creations
                 remainings = []
                 for source, sourcerev, dest in pendings:
                     tagname = dest.split('/')[-1]
                     if source.startswith(srctagspath):
                         remainings.append([source, sourcerev, tagname])
                         continue
                     if tagname in tags:
                         # Keep the latest tag value
                         continue
                     # From revision may be fake, get one with changes
                     try:
                         tagid = self.latest(source, sourcerev)
                         if tagid and tagname not in tags:
                             tags[tagname] = tagid
                     except SvnPathNotFound:
                         # It happens when we are following directories
                         # we assumed were copied with their parents
                         # but were really created in the tag
                         # directory.
                         pass
                 pendings = remainings
                 tagspath = srctagspath
 
         except SubversionException:
             self.ui.note(_('no tags found at revision %d\n') % start)
         return tags
 
     def converted(self, rev, destrev):
         if not self.wc:
             return
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.wc, '.svn', 'hg-shamap'),
                                   'a')
         self.convertfp.write('%s %d\n' % (destrev, self.revnum(rev)))
         self.convertfp.flush()
 
     def revid(self, revnum, module=None):
         return 'svn:%s%s@%s' % (self.uuid, module or self.module, revnum)
 
     def revnum(self, rev):
         return int(rev.split('@')[-1])
 
     def revsplit(self, rev):
         url, revnum = rev.rsplit('@', 1)
         revnum = int(revnum)
         parts = url.split('/', 1)
         uuid = parts.pop(0)[4:]
         mod = ''
         if parts:
             mod = '/' + parts[0]
         return uuid, mod, revnum
 
     def latest(self, path, stop=0):
         """Find the latest revid affecting path, up to stop. It may return
         a revision in a different module, since a branch may be moved without
         a change being reported. Return None if computed module does not
         belong to rootmodule subtree.
         """
         if not path.startswith(self.rootmodule):
             # Requests on foreign branches may be forbidden at server level
             self.ui.debug('ignoring foreign branch %r\n' % path)
             return None
 
         if not stop:
             stop = svn.ra.get_latest_revnum(self.ra)
         try:
             prevmodule = self.reparent('')
             dirent = svn.ra.stat(self.ra, path.strip('/'), stop)
             self.reparent(prevmodule)
         except SubversionException:
             dirent = None
         if not dirent:
             raise SvnPathNotFound(_('%s not found up to revision %d')
                                   % (path, stop))
 
         # stat() gives us the previous revision on this line of
         # development, but it might be in *another module*. Fetch the
         # log and detect renames down to the latest revision.
         stream = self._getlog([path], stop, dirent.created_rev)
         try:
             for entry in stream:
                 paths, revnum, author, date, message = entry
                 if revnum <= dirent.created_rev:
                     break
 
                 for p in paths:
                     if not path.startswith(p) or not paths[p].copyfrom_path:
                         continue
                     newpath = paths[p].copyfrom_path + path[len(p):]
                     self.ui.debug("branch renamed from %s to %s at %d\n" %
                                   (path, newpath, revnum))
                     path = newpath
                     break
         finally:
             stream.close()
 
         if not path.startswith(self.rootmodule):
             self.ui.debug('ignoring foreign branch %r\n' % path)
             return None
         return self.revid(dirent.created_rev, path)
 
     def reparent(self, module):
         """Reparent the svn transport and return the previous parent."""
         if self.prevmodule == module:
             return module
         svnurl = self.baseurl + urllib.quote(module)
         prevmodule = self.prevmodule
         if prevmodule is None:
             prevmodule = ''
         self.ui.debug("reparent to %s\n" % svnurl)
         svn.ra.reparent(self.ra, svnurl)
         self.prevmodule = module
         return prevmodule
 
     def expandpaths(self, rev, paths, parents):
         entries = []
         # Map of entrypath, revision for finding source of deleted
         # revisions.
         copyfrom = {}
         copies = {}
 
         new_module, revnum = self.revsplit(rev)[1:]
         if new_module != self.module:
             self.module = new_module
             self.reparent(self.module)
 
         for path, ent in paths:
             entrypath = self.getrelpath(path)
 
             kind = self._checkpath(entrypath, revnum)
             if kind == svn.core.svn_node_file:
                 entries.append(self.recode(entrypath))
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = self.revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrom_path = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrom_path:
                     continue
                 self.ui.debug("copied to %s from %s@%s\n" %
                               (entrypath, copyfrom_path, ent.copyfrom_rev))
                 copies[self.recode(entrypath)] = self.recode(copyfrom_path)
             elif kind == 0: # gone, but had better be a deleted *file*
                 self.ui.debug("gone from %s\n" % ent.copyfrom_rev)
                 pmodule, prevnum = self.revsplit(parents[0])[1:]
                 parentpath = pmodule + "/" + entrypath
                 self.ui.debug("entry %s\n" % parentpath)
 
                 # We can avoid the reparent calls if the module has
                 # not changed but it probably does not worth the pain.
                 prevmodule = self.reparent('')
                 fromkind = svn.ra.check_path(self.ra, parentpath.strip('/'),
                                              prevnum)
                 self.reparent(prevmodule)
 
                 if fromkind == svn.core.svn_node_file:
                     entries.append(self.recode(entrypath))
                 elif fromkind == svn.core.svn_node_dir:
                     if ent.action == 'C':
                         children = self._find_children(path, prevnum)
                     else:
                         oroot = parentpath.strip('/')
                         nroot = path.strip('/')
                         children = self._find_children(oroot, prevnum)
                         children = [s.replace(oroot, nroot) for s in children]
 
                     for child in children:
                         childpath = self.getrelpath("/" + child, pmodule)
                         if not childpath:
                             continue
                         if childpath in copies:
                             del copies[childpath]
                         entries.append(childpath)
                 else:
                     self.ui.debug('unknown path in revision %d: %s\n' % \
                                   (revnum, path))
             elif kind == svn.core.svn_node_dir:
                 # If the directory just had a prop change,
                 # then we shouldn't need to look for its children.
                 if ent.action == 'M':
                     continue
 
                 children = sorted(self._find_children(path, revnum))
                 for child in children:
                     # Can we move a child directory and its
                     # parent in the same commit? (probably can). Could
                     # cause problems if instead of revnum -1,
                     # we have to look in (copyfrom_path, revnum - 1)
                     entrypath = self.getrelpath("/" + child)
                     if entrypath:
                         # Need to filter out directories here...
                         kind = self._checkpath(entrypath, revnum)
                         if kind != svn.core.svn_node_dir:
                             entries.append(self.recode(entrypath))
 
                 # Handle directory copies
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = self.revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrompath = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrompath:
                     continue
                 copyfrom[path] = ent
                 self.ui.debug("mark %s came from %s:%d\n"
                               % (path, copyfrompath, ent.copyfrom_rev))
                 children = self._find_children(ent.copyfrom_path, ent.copyfrom_rev)
                 children.sort()
                 for child in children:
                     entrypath = self.getrelpath("/" + child, pmodule)
                     if not entrypath:
                         continue
                     copytopath = path + entrypath[len(copyfrompath):]
                     copytopath = self.getrelpath(copytopath)
                     copies[self.recode(copytopath)] = self.recode(entrypath)
 
         return (list(set(entries)), copies)
 
     def _fetch_revisions(self, from_revnum, to_revnum):
         if from_revnum < to_revnum:
             from_revnum, to_revnum = to_revnum, from_revnum
 
         self.child_cset = None
 
         def parselogentry(orig_paths, revnum, author, date, message):
             """Return the parsed commit object or None, and True if
             the revision is a branch root.
             """
             self.ui.debug("parsing revision %d (%d changes)\n" %
                           (revnum, len(orig_paths)))
 
             branched = False
             rev = self.revid(revnum)
             # branch log might return entries for a parent we already have
 
             if rev in self.commits or revnum < to_revnum:
                 return None, branched
 
             parents = []
             # check whether this revision is the start of a branch or part
             # of a branch renaming
             orig_paths = sorted(orig_paths.iteritems())
             root_paths = [(p, e) for p, e in orig_paths
                           if self.module.startswith(p)]
             if root_paths:
                 path, ent = root_paths[-1]
                 if ent.copyfrom_path:
                     branched = True
                     newpath = ent.copyfrom_path + self.module[len(path):]
                     # ent.copyfrom_rev may not be the actual last revision
                     previd = self.latest(newpath, ent.copyfrom_rev)
                     if previd is not None:
                         prevmodule, prevnum = self.revsplit(previd)[1:]
                         if prevnum >= self.startrev:
                             parents = [previd]
                             self.ui.note(
                                 _('found parent of branch %s at %d: %s\n') %
                                 (self.module, prevnum, prevmodule))
                 else:
                     self.ui.debug("no copyfrom path, don't know what to do.\n")
 
             paths = []
             # filter out unrelated paths
             for path, ent in orig_paths:
                 if self.getrelpath(path) is None:
                     continue
                 paths.append((path, ent))
 
             # Example SVN datetime. Includes microseconds.
             # ISO-8601 conformant
             # '2007-01-04T17:35:00.902377Z'
             date = util.parsedate(date[:19] + " UTC", ["%Y-%m-%dT%H:%M:%S"])
 
             log = message and self.recode(message) or ''
             author = author and self.recode(author) or ''
             try:
                 branch = self.module.split("/")[-1]
                 if branch == 'trunk':
                     branch = ''
             except IndexError:
                 branch = None
 
             cset = commit(author=author,
                           date=util.datestr(date),
                           desc=log,
                           parents=parents,
                           branch=branch,
                           rev=rev)
 
             self.commits[rev] = cset
             # The parents list is *shared* among self.paths and the
             # commit object. Both will be updated below.
             self.paths[rev] = (paths, cset.parents)
             if self.child_cset and not self.child_cset.parents:
                 self.child_cset.parents[:] = [rev]
             self.child_cset = cset
             return cset, branched
 
         self.ui.note(_('fetching revision log for "%s" from %d to %d\n') %
                      (self.module, from_revnum, to_revnum))
 
         try:
             firstcset = None
             lastonbranch = False
             stream = self._getlog([self.module], from_revnum, to_revnum)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if revnum < self.startrev:
                         lastonbranch = True
                         break
                     if not paths:
                         self.ui.debug('revision %d has no entries\n' % revnum)
                         # If we ever leave the loop on an empty
                         # revision, do not try to get a parent branch
                         lastonbranch = lastonbranch or revnum == 0
                         continue
                     cset, lastonbranch = parselogentry(paths, revnum, author,
                                                        date, message)
                     if cset:
                         firstcset = cset
                     if lastonbranch:
                         break
             finally:
                 stream.close()
 
             if not lastonbranch and firstcset and not firstcset.parents:
                 # The first revision of the sequence (the last fetched one)
                 # has invalid parents if not a branch root. Find the parent
                 # revision now, if any.
                 try:
                     firstrevnum = self.revnum(firstcset.rev)
                     if firstrevnum > 1:
                         latest = self.latest(self.module, firstrevnum - 1)
                         if latest:
                             firstcset.parents.append(latest)
                 except SvnPathNotFound:
                     pass
         except SubversionException, (inst, num):
             if num == svn.core.SVN_ERR_FS_NO_SUCH_REVISION:
                 raise util.Abort(_('svn: branch has no revision %s') % to_revnum)
             raise
 
     def _getfile(self, file, rev):
         # TODO: ra.get_file transmits the whole file instead of diffs.
         mode = ''
         try:
             new_module, revnum = self.revsplit(rev)[1:]
             if self.module != new_module:
                 self.module = new_module
                 self.reparent(self.module)
             io = StringIO()
             info = svn.ra.get_file(self.ra, file, revnum, io)
             data = io.getvalue()
             # ra.get_files() seems to keep a reference on the input buffer
             # preventing collection. Release it explicitely.
             io.close()
             if isinstance(info, list):
                 info = info[-1]
             mode = ("svn:executable" in info) and 'x' or ''
             mode = ("svn:special" in info) and 'l' or mode
         except SubversionException, e:
             notfound = (svn.core.SVN_ERR_FS_NOT_FOUND,
                 svn.core.SVN_ERR_RA_DAV_PATH_NOT_FOUND)
             if e.apr_err in notfound: # File not found
                 raise IOError()
             raise
         if mode == 'l':
             link_prefix = "link "
             if data.startswith(link_prefix):
                 data = data[len(link_prefix):]
         return data, mode
 
     def _find_children(self, path, revnum):
         path = path.strip('/')
         pool = Pool()
         rpath = '/'.join([self.baseurl, urllib.quote(path)]).strip('/')
         return ['%s/%s' % (path, x) for x in
                 svn.client.ls(rpath, optrev(revnum), True, self.ctx, pool).keys()]
 
     def getrelpath(self, path, module=None):
         if module is None:
             module = self.module
         # Given the repository url of this wc, say
         #   "http://server/plone/CMFPlone/branches/Plone-2_0-branch"
         # extract the "entry" portion (a relative path) from what
         # svn log --xml says, ie
         #   "/CMFPlone/branches/Plone-2_0-branch/tests/PloneTestCase.py"
         # that is to say "tests/PloneTestCase.py"
         if path.startswith(module):
             relative = path.rstrip('/')[len(module):]
             if relative.startswith('/'):
                 return relative[1:]
             elif relative == '':
                 return relative
 
         # The path is outside our tracked tree...
         self.ui.debug('%r is not under %r, ignoring\n' % (path, module))
         return None
 
     def _checkpath(self, path, revnum):
         # ra.check_path does not like leading slashes very much, it leads
         # to PROPFIND subversion errors
         return svn.ra.check_path(self.ra, path.strip('/'), revnum)
 
     def _getlog(self, paths, start, end, limit=0, discover_changed_paths=True,
                 strict_node_history=False):
         # Normalize path names, svn >= 1.5 only wants paths relative to
         # supplied URL
         relpaths = []
         for p in paths:
             if not p.startswith('/'):
                 p = self.module + '/' + p
             relpaths.append(p.strip('/'))
         args = [self.baseurl, relpaths, start, end, limit, discover_changed_paths,
                 strict_node_history]
         arg = encodeargs(args)
         hgexe = util.hgexecutable()
         cmd = '%s debugsvnlog' % util.shellquote(hgexe)
         stdin, stdout = util.popen2(cmd)
         stdin.write(arg)
         try:
             stdin.close()
         except IOError:
             raise util.Abort(_('Mercurial failed to run itself, check'
                                ' hg executable is in PATH'))
         return logstream(stdout)
 
 pre_revprop_change = '''#!/bin/sh
 
 REPOS="$1"
 REV="$2"
 USER="$3"
 PROPNAME="$4"
 ACTION="$5"
 
 if [ "$ACTION" = "M" -a "$PROPNAME" = "svn:log" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-branch" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-rev" ]; then exit 0; fi
 
 echo "Changing prohibited revision property" >&2
 exit 1
 '''
 
 class svn_sink(converter_sink, commandline):
     commit_re = re.compile(r'Committed revision (\d+).', re.M)
 
     def prerun(self):
         if self.wc:
             os.chdir(self.wc)
 
     def postrun(self):
         if self.wc:
             os.chdir(self.cwd)
 
     def join(self, name):
         return os.path.join(self.wc, '.svn', name)
 
     def revmapfile(self):
         return self.join('hg-shamap')
 
     def authorfile(self):
         return self.join('hg-authormap')
 
     def __init__(self, ui, path):
         converter_sink.__init__(self, ui, path)
         commandline.__init__(self, ui, 'svn')
         self.delete = []
         self.setexec = []
         self.delexec = []
         self.copies = []
         self.wc = None
         self.cwd = os.getcwd()
 
         path = os.path.realpath(path)
 
         created = False
         if os.path.isfile(os.path.join(path, '.svn', 'entries')):
             self.wc = path
             self.run0('update')
         else:
             wcpath = os.path.join(os.getcwd(), os.path.basename(path) + '-wc')
 
             if os.path.isdir(os.path.dirname(path)):
                 if not os.path.exists(os.path.join(path, 'db', 'fs-type')):
-                    ui.status(_('initializing svn repo %r\n') %
+                    ui.status(_('initializing svn repository %r\n') %
                               os.path.basename(path))
                     commandline(ui, 'svnadmin').run0('create', path)
                     created = path
                 path = util.normpath(path)
                 if not path.startswith('/'):
                     path = '/' + path
                 path = 'file://' + path
 
             ui.status(_('initializing svn wc %r\n') % os.path.basename(wcpath))
             self.run0('checkout', path, wcpath)
 
             self.wc = wcpath
         self.opener = util.opener(self.wc)
         self.wopener = util.opener(self.wc)
         self.childmap = mapfile(ui, self.join('hg-childmap'))
         self.is_exec = util.checkexec(self.wc) and util.is_exec or None
 
         if created:
             hook = os.path.join(created, 'hooks', 'pre-revprop-change')
             fp = open(hook, 'w')
             fp.write(pre_revprop_change)
             fp.close()
             util.set_flags(hook, False, True)
 
         xport = transport.SvnRaTransport(url=geturl(path))
         self.uuid = svn.ra.get_uuid(xport.ra)
 
     def wjoin(self, *names):
         return os.path.join(self.wc, *names)
 
     def putfile(self, filename, flags, data):
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             try:
                 if os.path.islink(self.wjoin(filename)):
                     os.unlink(filename)
             except OSError:
                 pass
             self.wopener(filename, 'w').write(data)
 
             if self.is_exec:
                 was_exec = self.is_exec(self.wjoin(filename))
             else:
                 # On filesystems not supporting execute-bit, there is no way
                 # to know if it is set but asking subversion. Setting it
                 # systematically is just as expensive and much simpler.
                 was_exec = 'x' not in flags
 
             util.set_flags(self.wjoin(filename), False, 'x' in flags)
             if was_exec:
                 if 'x' not in flags:
                     self.delexec.append(filename)
             else:
                 if 'x' in flags:
                     self.setexec.append(filename)
 
     def _copyfile(self, source, dest):
         # SVN's copy command pukes if the destination file exists, but
         # our copyfile method expects to record a copy that has
         # already occurred.  Cross the semantic gap.
         wdest = self.wjoin(dest)
         exists = os.path.exists(wdest)
         if exists:
             fd, tempname = tempfile.mkstemp(
                 prefix='hg-copy-', dir=os.path.dirname(wdest))
             os.close(fd)
             os.unlink(tempname)
             os.rename(wdest, tempname)
         try:
             self.run0('copy', source, dest)
         finally:
             if exists:
                 try:
                     os.unlink(wdest)
                 except OSError:
                     pass
                 os.rename(tempname, wdest)
 
     def dirs_of(self, files):
         dirs = set()
         for f in files:
             if os.path.isdir(self.wjoin(f)):
                 dirs.add(f)
             for i in strutil.rfindall(f, '/'):
                 dirs.add(f[:i])
         return dirs
 
     def add_dirs(self, files):
         add_dirs = [d for d in sorted(self.dirs_of(files))
                     if not os.path.exists(self.wjoin(d, '.svn', 'entries'))]
         if add_dirs:
             self.xargs(add_dirs, 'add', non_recursive=True, quiet=True)
         return add_dirs
 
     def add_files(self, files):
         if files:
             self.xargs(files, 'add', quiet=True)
         return files
 
     def tidy_dirs(self, names):
         deleted = []
         for d in sorted(self.dirs_of(names), reverse=True):
             wd = self.wjoin(d)
             if os.listdir(wd) == '.svn':
                 self.run0('delete', d)
                 deleted.append(d)
         return deleted
 
     def addchild(self, parent, child):
         self.childmap[parent] = child
 
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
     def putcommit(self, files, copies, parents, commit, source, revmap):
         # Apply changes to working copy
         for f, v in files:
             try:
                 data = source.getfile(f, v)
             except IOError:
                 self.delete.append(f)
             else:
                 e = source.getmode(f, v)
                 self.putfile(f, e, data)
                 if f in copies:
                     self.copies.append([copies[f], f])
         files = [f[0] for f in files]
 
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])
             except KeyError:
                 pass
         entries = set(self.delete)
         files = frozenset(files)
         entries.update(self.add_dirs(files.difference(entries)))
         if self.copies:
             for s, d in self.copies:
                 self._copyfile(s, d)
             self.copies = []
         if self.delete:
             self.xargs(self.delete, 'delete')
             self.delete = []
         entries.update(self.add_files(files.difference(entries)))
         entries.update(self.tidy_dirs(entries))
         if self.delexec:
             self.xargs(self.delexec, 'propdel', 'svn:executable')
             self.delexec = []
         if self.setexec:
             self.xargs(self.setexec, 'propset', 'svn:executable', '*')
             self.setexec = []
 
         fd, messagefile = tempfile.mkstemp(prefix='hg-convert-')
         fp = os.fdopen(fd, 'w')
         fp.write(commit.desc)
         fp.close()
         try:
             output = self.run0('commit',
                                username=util.shortuser(commit.author),
                                file=messagefile,
                                encoding='utf-8')
             try:
                 rev = self.commit_re.search(output).group(1)
             except AttributeError:
                 if not files:
                     return parents[0]
                 self.ui.warn(_('unexpected svn output:\n'))
                 self.ui.warn(output)
                 raise util.Abort(_('unable to cope with svn output'))
             if commit.rev:
                 self.run('propset', 'hg:convert-rev', commit.rev,
                          revprop=True, revision=rev)
             if commit.branch and commit.branch != 'default':
                 self.run('propset', 'hg:convert-branch', commit.branch,
                          revprop=True, revision=rev)
             for parent in parents:
                 self.addchild(parent, rev)
             return self.revid(rev)
         finally:
             os.unlink(messagefile)
 
     def puttags(self, tags):
         self.ui.warn(_('XXX TAGS NOT IMPLEMENTED YET\n'))

tests/test-convert-svn-sink.out

@@ -1,337 +1,337 b''
 % add
 adding a
 adding d1/d2/b
 % modify
 1:e0e2b8a9156b
 assuming destination a-hg
-initializing svn repo 'a-hg'
+initializing svn repository 'a-hg'
 initializing svn wc 'a-hg-wc'
 scanning source...
 sorting...
 converting...
 1 add a file
 0 modify a file
 At revision 2.
  2 2 test .
  2 2 test a
  2 1 test d1
  2 1 test d1/d2
  2 1 test d1/d2/b
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="2">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="M">/a</path>
 </paths>
 <msg>modify a file</msg>
 </logentry>
 <logentry
    revision="1">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="A">/a</path>
 <path
    action="A">/d1</path>
 <path
    action="A">/d1/d2</path>
 <path
    action="A">/d1/d2/b</path>
 </paths>
 <msg>add a file</msg>
 </logentry>
 </log>
 a:
 a
 d1
 
 a-hg-wc:
 a
 d1
 same
 % rename
 2:eb5169441d43
 assuming destination a-hg
 initializing svn wc 'a-hg-wc'
 scanning source...
 sorting...
 converting...
 0 rename a file
 At revision 3.
  3 3 test .
  3 3 test b
  3 1 test d1
  3 1 test d1/d2
  3 1 test d1/d2/b
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="3">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="D">/a</path>
 <path
    copyfrom-path="/a"
    copyfrom-rev="2"
    action="A">/b</path>
 </paths>
 <msg>rename a file</msg>
 </logentry>
 </log>
 a:
 b
 d1
 
 a-hg-wc:
 b
 d1
 % copy
 3:60effef6ab48
 assuming destination a-hg
 initializing svn wc 'a-hg-wc'
 scanning source...
 sorting...
 converting...
 0 copy a file
 At revision 4.
  4 4 test .
  4 3 test b
  4 4 test c
  4 1 test d1
  4 1 test d1/d2
  4 1 test d1/d2/b
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="4">
 <author>test</author>
 <date/>
 <paths>
 <path
    copyfrom-path="/b"
    copyfrom-rev="3"
    action="A">/c</path>
 </paths>
 <msg>copy a file</msg>
 </logentry>
 </log>
 a:
 b
 c
 d1
 
 a-hg-wc:
 b
 c
 d1
 % remove
 4:87bbe3013fb6
 assuming destination a-hg
 initializing svn wc 'a-hg-wc'
 scanning source...
 sorting...
 converting...
 0 remove a file
 At revision 5.
  5 5 test .
  5 4 test c
  5 1 test d1
  5 1 test d1/d2
  5 1 test d1/d2/b
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="5">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="D">/b</path>
 </paths>
 <msg>remove a file</msg>
 </logentry>
 </log>
 a:
 c
 d1
 
 a-hg-wc:
 c
 d1
 % executable
 5:ff42e473c340
 assuming destination a-hg
 initializing svn wc 'a-hg-wc'
 scanning source...
 sorting...
 converting...
 0 make a file executable
 At revision 6.
  6 6 test .
  6 6 test c
  6 1 test d1
  6 1 test d1/d2
  6 1 test d1/d2/b
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="6">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="M">/c</path>
 </paths>
 <msg>make a file executable</msg>
 </logentry>
 </log>
 executable
 % executable in new directory
 adding d1/a
 assuming destination a-hg
-initializing svn repo 'a-hg'
+initializing svn repository 'a-hg'
 initializing svn wc 'a-hg-wc'
 scanning source...
 sorting...
 converting...
 0 add executable file in new directory
 At revision 1.
  1 1 test .
  1 1 test d1
  1 1 test d1/a
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="1">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="A">/d1</path>
 <path
    action="A">/d1/a</path>
 </paths>
 <msg>add executable file in new directory</msg>
 </logentry>
 </log>
 executable
 % copy to new directory
 assuming destination a-hg
 initializing svn wc 'a-hg-wc'
 scanning source...
 sorting...
 converting...
 0 copy file to new directory
 At revision 2.
  2 2 test .
  2 1 test d1
  2 1 test d1/a
  2 2 test d2
  2 2 test d2/a
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="2">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="A">/d2</path>
 <path
    copyfrom-path="/d1/a"
    copyfrom-rev="1"
    action="A">/d2/a</path>
 </paths>
 <msg>copy file to new directory</msg>
 </logentry>
 </log>
 % branchy history
 adding b
 adding left-1
 adding left-2
 1 files updated, 0 files merged, 2 files removed, 0 files unresolved
 adding right-1
 created new head
 adding right-2
 3 files updated, 0 files merged, 2 files removed, 0 files unresolved
 merging b
 warning: conflicts during merge.
 merging b failed!
 2 files updated, 0 files merged, 0 files removed, 1 files unresolved
 use 'hg resolve' to retry unresolved file merges or 'hg update -C' to abandon
 assuming destination b-hg
-initializing svn repo 'b-hg'
+initializing svn repository 'b-hg'
 initializing svn wc 'b-hg-wc'
 scanning source...
 sorting...
 converting...
 5 base
 4 left-1
 3 left-2
 2 right-1
 1 right-2
 0 merge
 % expect 4 changes
 At revision 4.
  4 4 test .
  4 3 test b
  4 2 test left-1
  4 3 test left-2
  4 4 test right-1
  4 4 test right-2
 <?xml version="1.0"?>
 <log>
 <logentry
    revision="4">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="A">/right-1</path>
 <path
    action="A">/right-2</path>
 </paths>
 <msg>merge</msg>
 </logentry>
 <logentry
    revision="3">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="M">/b</path>
 <path
    action="A">/left-2</path>
 </paths>
 <msg>left-2</msg>
 </logentry>
 <logentry
    revision="2">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="M">/b</path>
 <path
    action="A">/left-1</path>
 </paths>
 <msg>left-1</msg>
 </logentry>
 <logentry
    revision="1">
 <author>test</author>
 <date/>
 <paths>
 <path
    action="A">/b</path>
 </paths>
 <msg>base</msg>
 </logentry>
 </log>

tests/test-convert.out

@@ -1,291 +1,291 b''
 hg convert [OPTION]... SOURCE [DEST [REVMAP]]
 
 convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
 
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
     - Bazaar [bzr]
     - Perforce [p4]
 
     Accepted destination formats [identifiers]:
 
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted. Otherwise,
     convert will only import up to the named revision (given in a format
     understood by the source).
 
     If no destination directory name is specified, it defaults to the basename
     of the source with '-hg' appended. If the destination repository doesn't
     exist, it will be created.
 
     By default, all sources except Mercurial will use --branchsort. Mercurial
     uses --sourcesort to preserve original revision numbers order. Sort modes
     have the following effects:
 
     --branchsort  convert from parent to child revision when possible, which
                   means branches are usually converted one after the other. It
                   generates more compact repositories.
     --datesort    sort revisions by date. Converted repositories have good-
                   looking changelogs but are often an order of magnitude
                   larger than the same ones generated by --branchsort.
     --sourcesort  try to preserve source revisions order, only supported by
                   Mercurial sources.
 
     If <REVMAP> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default). The <REVMAP> is a simple text file that
     maps each source commit ID to the destination ID for that revision, like
     so:
 
       <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created. It's updated on
     each commit copied, so convert-repo can be interrupted and can be run
     repeatedly to copy new commits.
 
     The [username mapping] file is a simple text file that maps each source
     commit author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (eg: CVS). One line per author
     mapping and the line format is: srcauthor=whatever string you want
 
     The filemap is a file that allows filtering and remapping of files and
     directories. Comment lines start with '#'. Each line can contain one of
     the following directives:
 
       include path/to/file
 
       exclude path/to/file
 
       rename from/file to/file
 
     The 'include' directive causes a file, or all files under a directory, to
     be included in the destination repository, and the exclusion of all other
     files and directories not explicitly included. The 'exclude' directive
     causes files or directories to be omitted. The 'rename' directive renames
     a file or directory. To rename from a subdirectory into the root of the
     repository, use '.' as the path to rename to.
 
     The splicemap is a file that allows insertion of synthetic history,
     letting you specify the parents of a revision. This is useful if you want
     to e.g. give a Subversion merge two parents, or graft two disconnected
     series of history together. Each entry contains a key, followed by a
     space, followed by one or two comma-separated values. The key is the
     revision ID in the source revision control system whose parents should be
     modified (same format as a key in .hg/shamap). The values are the revision
     IDs (in either the source or destination revision control system) that
     should be used as the new parents for that node. For example, if you have
     merged "release-1.0" into "trunk", then you should specify the revision on
     "trunk" as the first parent and the one on the "release-1.0" branch as the
     second.
 
     The branchmap is a file that allows you to rename a branch when it is
     being brought in from whatever external repository. When used in
     conjunction with a splicemap, it allows for a powerful combination to help
     fix even the most badly mismanaged repositories and turn them into nicely
     structured Mercurial repositories. The branchmap contains lines of the
     form "original_branch_name new_branch_name". "original_branch_name" is the
     name of the branch in the source repository, and "new_branch_name" is the
     name of the branch is the destination repository. This can be used to (for
     instance) move code in one repository from "default" to a named branch.
 
     Mercurial Source
     ----------------
 
     --config convert.hg.ignoreerrors=False    (boolean)
         ignore integrity errors when reading. Use it to fix Mercurial
         repositories with missing revlogs, by converting from and to
         Mercurial.
     --config convert.hg.saverev=False         (boolean)
         store original revision ID in changeset (forces target IDs to change)
     --config convert.hg.startrev=0            (hg revision identifier)
         convert start revision and its descendants
 
     CVS Source
     ----------
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS to
     indicate the starting point of what will be converted. Direct access to
     the repository files is not needed, unless of course the repository is
     :local:. The conversion uses the top level directory in the sandbox to
     find the CVS repository, and then uses CVS rlog commands to find files to
     convert. This means that unless a filemap is given, all files under the
     starting directory will be converted, and that any directory
     reorganization in the CVS sandbox is ignored.
 
     The options shown are the defaults.
 
     --config convert.cvsps.cache=True         (boolean)
         Set to False to disable remote log caching, for testing and debugging
         purposes.
     --config convert.cvsps.fuzz=60            (integer)
         Specify the maximum time (in seconds) that is allowed between commits
         with identical user and log message in a single changeset. When very
         large files were checked in as part of a changeset then the default
         may not be long enough.
     --config convert.cvsps.mergeto='{{mergetobranch ([-\w]+)}}'
         Specify a regular expression to which commit log messages are matched.
         If a match occurs, then the conversion process will insert a dummy
         revision merging the branch on which this log message occurs to the
         branch indicated in the regex.
     --config convert.cvsps.mergefrom='{{mergefrombranch ([-\w]+)}}'
         Specify a regular expression to which commit log messages are matched.
         If a match occurs, then the conversion process will add the most
         recent revision on the branch indicated in the regex as the second
         parent of the changeset.
     --config hook.cvslog
         Specify a Python function to be called at the end of gathering the CVS
         log. The function is passed a list with the log entries, and can
         modify the entries in-place, or add or delete them.
     --config hook.cvschangesets
         Specify a Python function to be called after the changesets are
         calculated from the the CVS log. The function is passed a list with
         the changeset entries, and can modify the changesets in-place, or add
         or delete them.
 
     An additional "debugcvsps" Mercurial command allows the builtin changeset
     merging code to be run without doing a conversion. Its parameters and
     output are similar to that of cvsps 2.1. Please see the command help for
     more details.
 
     Subversion Source
     -----------------
 
     Subversion source detects classical trunk/branches/tags layouts. By
     default, the supplied "svn://repo/path/" source URL is converted as a
     single branch. If "svn://repo/path/trunk" exists it replaces the default
     branch. If "svn://repo/path/branches" exists, its subdirectories are
     listed as possible branches. If "svn://repo/path/tags" exists, it is
     looked for tags referencing converted branches. Default "trunk",
     "branches" and "tags" values can be overridden with following options. Set
     them to paths relative to the source URL, or leave them blank to disable
     auto detection.
 
     --config convert.svn.branches=branches    (directory name)
         specify the directory containing branches
     --config convert.svn.tags=tags            (directory name)
         specify the directory containing tags
     --config convert.svn.trunk=trunk          (directory name)
         specify the name of the trunk branch
 
     Source history can be retrieved starting at a specific revision, instead
     of being integrally converted. Only single branch conversions are
     supported.
 
     --config convert.svn.startrev=0           (svn revision number)
         specify start Subversion revision.
 
     Perforce Source
     ---------------
 
     The Perforce (P4) importer can be given a p4 depot path or a client
     specification as source. It will convert all files in the source to a flat
     Mercurial repository, ignoring labels, branches and integrations. Note
     that when a depot path is given you then usually should specify a target
     directory, because otherwise the target may be named ...-hg.
 
     It is possible to limit the amount of source history to be converted by
     specifying an initial Perforce revision.
 
     --config convert.p4.startrev=0            (perforce changelist number)
         specify initial Perforce revision.
 
     Mercurial Destination
     ---------------------
 
     --config convert.hg.clonebranches=False   (boolean)
         dispatch source branches in separate clones.
     --config convert.hg.tagsbranch=default    (branch name)
         tag revisions branch name
     --config convert.hg.usebranchnames=True   (boolean)
         preserve branch names
 
 options:
 
  -A --authors      username mapping filename
  -d --dest-type    destination repository type
     --filemap      remap file names using contents of file
  -r --rev          import up to target revision REV
  -s --source-type  source repository type
     --splicemap    splice synthesized history into place
     --branchmap    change branch names while converting
     --branchsort   try to sort changesets by branches
     --datesort     try to sort changesets by date
     --sourcesort   preserve source changesets order
 
 use "hg -v help convert" to show global options
 adding a
 assuming destination a-hg
 initializing destination a-hg repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 pulling from ../a
 searching for changes
 no changes found
 % should fail
 initializing destination bogusfile repository
 abort: cannot create new bundle repository
 % should fail
 abort: Permission denied: bogusdir
 % should succeed
 initializing destination bogusdir repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 % test pre and post conversion actions
 run hg source pre-conversion action
 run hg sink pre-conversion action
 run hg sink post-conversion action
 run hg source post-conversion action
 % converting empty dir should fail nicely
 assuming destination emptydir-hg
 initializing destination emptydir-hg repository
 emptydir does not look like a CVS checkout
-emptydir does not look like a Git repo
-emptydir does not look like a Subversion repo
-emptydir is not a local Mercurial repo
-emptydir does not look like a darcs repo
-emptydir does not look like a monotone repo
-emptydir does not look like a GNU Arch repo
-emptydir does not look like a Bazaar repo
+emptydir does not look like a Git repository
+emptydir does not look like a Subversion repository
+emptydir is not a local Mercurial repository
+emptydir does not look like a darcs repository
+emptydir does not look like a monotone repository
+emptydir does not look like a GNU Arch repository
+emptydir does not look like a Bazaar repository
 cannot find required "p4" tool
 abort: emptydir: missing or unsupported repository
 % convert with imaginary source type
 initializing destination a-foo repository
 abort: foo: invalid source repository type
 % convert with imaginary sink type
 abort: foo: invalid destination repository type
 
 % testing: convert must not produce duplicate entries in fncache
 initializing destination b repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 % contents of fncache file:
 data/a.i
 data/b.i
 % test bogus URL
 abort: bzr+ssh://[e-mail]/baz: missing or unsupported repository