# or
# % git clone bzr::lp:myrepo
#
+# If you want to specify which branches you want track (per repo):
+# git config remote-bzr.branches 'trunk, devel, test'
+#
import sys
import bzrlib.generate_ids
import bzrlib.transport
+import bzrlib.errors
+import bzrlib.ui
+import bzrlib.urlutils
+import bzrlib.branch
import sys
import os
import json
import re
import StringIO
+import atexit, shutil, hashlib, urlparse, subprocess
NAME_RE = re.compile('^([^<>]+)')
AUTHOR_RE = re.compile('^([^<>]+?)? ?<([^<>]*)>$')
+EMAIL_RE = re.compile('^([^<>]+[^ \\\t<>])?\\b(?:[ \\t<>]*?)\\b([^ \\t<>]+@[^ \\t<>]+)')
RAW_AUTHOR_RE = re.compile('^(\w+) (.+)? <(.*)> (\d+) ([+-]\d+)')
def die(msg, *args):
def gittz(tz):
return '%+03d%02d' % (tz / 3600, tz % 3600 / 60)
+def get_config(config):
+ cmd = ['git', 'config', '--get', config]
+ process = subprocess.Popen(cmd, stdout=subprocess.PIPE)
+ output, _ = process.communicate()
+ return output
+
class Marks:
def __init__(self, path):
return self.marks[rev]
def to_rev(self, mark):
- return self.rev_marks[mark]
+ return str(self.rev_marks[mark])
def next_mark(self):
self.last_mark += 1
return self.last_mark
def is_marked(self, rev):
- return self.marks.has_key(rev)
+ return rev in self.marks
def new_mark(self, rev, mark):
self.marks[rev] = mark
name = m.group(1)
mail = m.group(2).strip()
else:
- m = NAME_RE.match(user)
+ m = EMAIL_RE.match(user)
if m:
- name = m.group(1).strip()
+ name = m.group(1)
+ mail = m.group(2)
+ else:
+ m = NAME_RE.match(user)
+ if m:
+ name = m.group(1).strip()
+
+ if not name:
+ name = 'unknown'
+ if not mail:
+ mail = 'Unknown'
return '%s <%s>' % (name, mail)
changes = cur.changes_from(prev)
+ def u(s):
+ return s.encode('utf-8')
+
for path, fid, kind in changes.added:
- modified[path] = fid
+ modified[u(path)] = fid
for path, fid, kind in changes.removed:
- removed[path] = None
+ removed[u(path)] = None
for path, fid, kind, mod, _ in changes.modified:
- modified[path] = fid
+ modified[u(path)] = fid
for oldpath, newpath, fid, kind, mod, _ in changes.renamed:
- removed[oldpath] = None
+ removed[u(oldpath)] = None
if kind == 'directory':
lst = cur.list_files(from_dir=newpath, recursive=True)
for path, file_class, kind, fid, entry in lst:
if kind != 'directory':
- modified[newpath + '/' + path] = fid
+ modified[u(newpath + '/' + path)] = fid
else:
- modified[newpath] = fid
+ modified[u(newpath)] = fid
return modified, removed
else:
mode = '100644'
- # is the blog already exported?
+ # is the blob already exported?
if h in filenodes:
mark = filenodes[h]
- final.append((mode, mark, path.encode('utf-8')))
+ final.append((mode, mark, path))
continue
d = tree.get_file_text(fid)
print "data %d" % len(d)
print d
- final.append((mode, mark, path.encode('utf-8')))
+ final.append((mode, mark, path))
return final
-def export_branch(branch, name):
- global prefix, dirname
+def export_branch(repo, name):
+ global prefix
ref = '%s/heads/%s' % (prefix, name)
tip = marks.get_tip(name)
+ branch = bzrlib.branch.Branch.open(branches[name])
repo = branch.repository
- repo.lock_read()
+
+ branch.lock_read()
revs = branch.iter_merge_sorted_revisions(None, tip, 'exclude', 'forward')
- count = 0
+ try:
+ tip_revno = branch.revision_id_to_revno(tip)
+ last_revno, _ = branch.last_revision_info()
+ total = last_revno - tip_revno
+ except bzrlib.errors.NoSuchRevision:
+ tip_revno = 0
+ total = 0
- revs = [revid for revid, _, _, _ in revs if not marks.is_marked(revid)]
+ for revid, _, seq, _ in revs:
- for revid in revs:
+ if marks.is_marked(revid):
+ continue
rev = repo.get_revision(revid)
+ revno = seq[0]
parents = rev.parent_ids
time = rev.timestamp
print "M %s :%u %s" % f
print
- count += 1
- if (count % 100 == 0):
- print "progress revision %s (%d/%d)" % (revid, count, len(revs))
- print "#############################################################"
+ if len(seq) > 1:
+ # let's skip branch revisions from the progress report
+ continue
+
+ progress = (revno - tip_revno)
+ if (progress % 100 == 0):
+ if total:
+ print "progress revision %d '%s' (%d/%d)" % (revno, name, progress, total)
+ else:
+ print "progress revision %d '%s' (%d)" % (revno, name, progress)
- repo.unlock()
+ branch.unlock()
revid = branch.last_revision()
marks.set_tip(name, revid)
def export_tag(repo, name):
- global tags
- try:
- print "reset refs/tags/%s" % name
- print "from :%u" % rev_to_mark(tags[name])
- print
- except KeyError:
- warn("TODO: fetch tag '%s'" % name)
+ global tags, prefix
+
+ ref = '%s/tags/%s' % (prefix, name)
+ print "reset %s" % ref
+ print "from :%u" % rev_to_mark(tags[name])
+ print
def do_import(parser):
global dirname
- branch = parser.repo
+ repo = parser.repo
path = os.path.join(dirname, 'marks-git')
print "feature done"
if os.path.exists(path):
print "feature import-marks=%s" % path
print "feature export-marks=%s" % path
+ print "feature force"
sys.stdout.flush()
while parser.check('import'):
ref = parser[1]
if ref.startswith('refs/heads/'):
name = ref[len('refs/heads/'):]
- export_branch(branch, name)
+ export_branch(repo, name)
if ref.startswith('refs/tags/'):
name = ref[len('refs/tags/'):]
- export_tag(branch, name)
+ export_tag(repo, name)
parser.next()
print 'done'
class CustomTree():
- def __init__(self, repo, revid, parents, files):
+ def __init__(self, branch, revid, parents, files):
global files_cache
- self.repo = repo
- self.revid = revid
- self.parents = parents
self.updates = {}
+ self.branch = branch
def copy_tree(revid):
files = files_cache[revid] = {}
- tree = repo.repository.revision_tree(revid)
- repo.lock_read()
+ branch.lock_read()
+ tree = branch.repository.revision_tree(revid)
try:
for path, entry in tree.iter_entries_by_dir():
- files[path] = entry.file_id
+ files[path] = [entry.file_id, None]
finally:
- repo.unlock()
+ branch.unlock()
return files
if len(parents) == 0:
self.base_files = copy_tree(self.base_id)
self.files = files_cache[revid] = self.base_files.copy()
+ self.rev_files = {}
+
+ for path, data in self.files.iteritems():
+ fid, mark = data
+ self.rev_files[fid] = [path, mark]
for path, f in files.iteritems():
- fid = self.files.get(path, None)
+ fid, mark = self.files.get(path, [None, None])
if not fid:
fid = bzrlib.generate_ids.gen_file_id(path)
f['path'] = path
+ self.rev_files[fid] = [path, mark]
self.updates[fid] = f
def last_revision(self):
changes = []
def get_parent(dirname, basename):
- parent_fid = self.base_files.get(dirname, None)
+ parent_fid, mark = self.base_files.get(dirname, [None, None])
if parent_fid:
return parent_fid
- parent_fid = self.files.get(dirname, None)
+ parent_fid, mark = self.files.get(dirname, [None, None])
if parent_fid:
return parent_fid
if basename == '':
return None
fid = bzrlib.generate_ids.gen_file_id(path)
- d = add_entry(fid, dirname, 'directory')
+ add_entry(fid, dirname, 'directory')
return fid
def add_entry(fid, path, kind, mode = None):
(None, basename),
(None, kind),
(None, executable))
- self.files[path] = change[0]
+ self.files[path] = [change[0], None]
changes.append(change)
- return change
def update_entry(fid, path, kind, mode = None):
dirname, basename = os.path.split(path)
(None, basename),
(None, kind),
(None, executable))
- self.files[path] = change[0]
+ self.files[path] = [change[0], None]
changes.append(change)
- return change
def remove_entry(fid, path, kind):
dirname, basename = os.path.split(path)
(None, None))
del self.files[path]
changes.append(change)
- return change
for fid, f in self.updates.iteritems():
path = f['path']
else:
add_entry(fid, path, 'file', f['mode'])
+ self.files[path][1] = f['mark']
+ self.rev_files[fid][1] = f['mark']
+
return changes
+ def get_content(self, file_id):
+ path, mark = self.rev_files[file_id]
+ if mark:
+ return blob_marks[mark]
+
+ # last resort
+ tree = self.branch.repository.revision_tree(self.base_id)
+ return tree.get_file_text(file_id)
+
def get_file_with_stat(self, file_id, path=None):
- return (StringIO.StringIO(self.updates[file_id]['data']), None)
+ content = self.get_content(file_id)
+ return (StringIO.StringIO(content), None)
def get_symlink_target(self, file_id):
- return self.updates[file_id]['data']
+ return self.get_content(file_id)
+
+ def id2path(self, file_id):
+ path, mark = self.rev_files[file_id]
+ return path
+
+def c_style_unescape(string):
+ if string[0] == string[-1] == '"':
+ return string.decode('string-escape')[1:-1]
+ return string
def parse_commit(parser):
- global marks, blob_marks, bmarks, parsed_refs
+ global marks, blob_marks, parsed_refs
global mode
parents = []
ref = parser[1]
parser.next()
- if ref != 'refs/heads/master':
- die("bzr doesn't support multiple branches; use 'master'")
+ if ref.startswith('refs/heads/'):
+ name = ref[len('refs/heads/'):]
+ branch = bzrlib.branch.Branch.open(branches[name])
+ else:
+ die('unknown ref')
commit_mark = parser.get_mark()
parser.next()
parents.append(parser.get_mark())
parser.next()
+ # fast-export adds an extra newline
+ if data[-1] == '\n':
+ data = data[:-1]
+
files = {}
for line in parser:
if parser.check('M'):
t, m, mark_ref, path = line.split(' ', 3)
mark = int(mark_ref[1:])
- f = { 'mode' : m, 'data' : blob_marks[mark] }
+ f = { 'mode' : m, 'mark' : mark }
elif parser.check('D'):
t, path = line.split(' ')
f = { 'deleted' : True }
else:
die('Unknown file command: %s' % line)
+ path = c_style_unescape(path).decode('utf-8')
files[path] = f
- repo = parser.repo
-
committer, date, tz = committer
- parents = [str(mark_to_rev(p)) for p in parents]
+ parents = [mark_to_rev(p) for p in parents]
revid = bzrlib.generate_ids.gen_revision_id(committer, date)
props = {}
- props['branch-nick'] = repo.nick
+ props['branch-nick'] = branch.nick
- mtree = CustomTree(repo, revid, parents, files)
+ mtree = CustomTree(branch, revid, parents, files)
changes = mtree.iter_changes()
- repo.lock_write()
+ branch.lock_write()
try:
- builder = repo.get_commit_builder(parents, None, date, tz, committer, props, revid)
+ builder = branch.get_commit_builder(parents, None, date, tz, committer, props, revid)
try:
list(builder.record_iter_changes(mtree, mtree.last_revision(), changes))
builder.finish_inventory()
builder.abort()
raise
finally:
- repo.unlock()
+ branch.unlock()
parsed_refs[ref] = revid
marks.new_mark(revid, commit_mark)
ref = parser[1]
parser.next()
- if ref != 'refs/heads/master':
- die("bzr doesn't support multiple branches; use 'master'")
-
# ugh
if parser.check('commit'):
parse_commit(parser)
parsed_refs[ref] = mark_to_rev(from_mark)
def do_export(parser):
- global parsed_refs, dirname, peer
+ global parsed_refs, dirname
parser.next()
else:
die('unhandled export command: %s' % line)
- repo = parser.repo
-
for ref, revid in parsed_refs.iteritems():
- if ref == 'refs/heads/master':
- repo.generate_revision_history(revid, marks.get_tip('master'))
- revno, revid = repo.last_revision_info()
- if peer:
- if hasattr(peer, "import_last_revision_info_and_tags"):
- peer.import_last_revision_info_and_tags(repo, revno, revid)
- else:
- peer.import_last_revision_info(repo.repository, revno, revid)
- else:
- wt = repo.bzrdir.open_workingtree()
+ if ref.startswith('refs/heads/'):
+ name = ref[len('refs/heads/'):]
+ branch = bzrlib.branch.Branch.open(branches[name])
+ branch.generate_revision_history(revid, marks.get_tip(name))
+
+ if name in peers:
+ peer = bzrlib.branch.Branch.open(peers[name])
+ try:
+ peer.bzrdir.push_branch(branch, revision_id=revid)
+ except bzrlib.errors.DivergedBranches:
+ print "error %s non-fast forward" % ref
+ continue
+
+ try:
+ wt = branch.bzrdir.open_workingtree()
wt.update()
+ except bzrlib.errors.NoWorkingTree:
+ pass
+ elif ref.startswith('refs/tags/'):
+ # TODO: implement tag push
+ print "error %s pushing tags not supported" % ref
+ continue
+ else:
+ # transport-helper/fast-export bugs
+ continue
+
print "ok %s" % ref
+
print
def do_capabilities(parser):
print "import"
print "export"
print "refspec refs/heads/*:%s/heads/*" % prefix
+ print "refspec refs/tags/*:%s/tags/*" % prefix
path = os.path.join(dirname, 'marks-git')
print
+def ref_is_valid(name):
+ return not True in [c in name for c in '~^: \\']
+
def do_list(parser):
global tags
- print "? refs/heads/%s" % 'master'
- history = parser.repo.revision_history()
- for tag, revid in parser.repo.tags.get_tag_dict().items():
- if revid not in history:
+ master_branch = None
+
+ for name in branches:
+ if not master_branch:
+ master_branch = name
+ print "? refs/heads/%s" % name
+
+ branch = bzrlib.branch.Branch.open(branches[master_branch])
+ branch.lock_read()
+ for tag, revid in branch.tags.get_tag_dict().items():
+ try:
+ branch.revision_id_to_dotted_revno(revid)
+ except bzrlib.errors.NoSuchRevision:
+ continue
+ if not ref_is_valid(tag):
continue
print "? refs/tags/%s" % tag
tags[tag] = revid
- print "@refs/heads/%s HEAD" % 'master'
+ branch.unlock()
+
+ print "@refs/heads/%s HEAD" % master_branch
print
+def get_remote_branch(origin, remote_branch, name):
+ global dirname, peers
+
+ branch_path = os.path.join(dirname, 'clone', name)
+ if os.path.exists(branch_path):
+ # pull
+ d = bzrlib.bzrdir.BzrDir.open(branch_path)
+ branch = d.open_branch()
+ try:
+ branch.pull(remote_branch, [], None, False)
+ except bzrlib.errors.DivergedBranches:
+ # use remote branch for now
+ return remote_branch
+ else:
+ # clone
+ d = origin.sprout(branch_path, None,
+ hardlink=True, create_tree_if_local=False,
+ force_new_repo=False,
+ source_branch=remote_branch)
+ branch = d.open_branch()
+
+ return branch
+
+def find_branches(repo, wanted):
+ transport = repo.bzrdir.root_transport
+
+ for fn in transport.iter_files_recursive():
+ if not fn.endswith('.bzr/branch-format'):
+ continue
+
+ name = subdir = fn[:-len('/.bzr/branch-format')]
+ name = name if name != '' else 'master'
+ name = name.replace('/', '+')
+
+ if wanted and not name in wanted:
+ continue
+
+ try:
+ cur = transport.clone(subdir)
+ branch = bzrlib.branch.Branch.open_from_transport(cur)
+ except bzrlib.errors.NotBranchError:
+ continue
+ else:
+ yield name, branch
+
def get_repo(url, alias):
- global dirname, peer
+ global dirname, peer, branches
+ normal_url = bzrlib.urlutils.normalize_url(url)
origin = bzrlib.bzrdir.BzrDir.open(url)
- branch = origin.open_branch()
+ is_local = isinstance(origin.transport, bzrlib.transport.local.LocalTransport)
+
+ shared_path = os.path.join(gitdir, 'bzr')
+ try:
+ shared_dir = bzrlib.bzrdir.BzrDir.open(shared_path)
+ except bzrlib.errors.NotBranchError:
+ shared_dir = bzrlib.bzrdir.BzrDir.create(shared_path)
+ try:
+ shared_repo = shared_dir.open_repository()
+ except bzrlib.errors.NoRepositoryPresent:
+ shared_repo = shared_dir.create_repository(shared=True)
- if not isinstance(origin.transport, bzrlib.transport.local.LocalTransport):
+ if not is_local:
clone_path = os.path.join(dirname, 'clone')
- remote_branch = branch
- if os.path.exists(clone_path):
- # pull
- d = bzrlib.bzrdir.BzrDir.open(clone_path)
- branch = d.open_branch()
- result = branch.pull(remote_branch, [], None, False)
+ if not os.path.exists(clone_path):
+ os.mkdir(clone_path)
else:
- # clone
- d = origin.sprout(clone_path, None,
- hardlink=True, create_tree_if_local=False,
- source_branch=remote_branch)
- branch = d.open_branch()
- branch.bind(remote_branch)
-
- peer = remote_branch
+ # check and remove old organization
+ try:
+ bdir = bzrlib.bzrdir.BzrDir.open(clone_path)
+ bdir.destroy_repository()
+ except bzrlib.errors.NotBranchError:
+ pass
+ except bzrlib.errors.NoRepositoryPresent:
+ pass
+
+ try:
+ repo = origin.open_repository()
+ if not repo.user_transport.listable():
+ # this repository is not usable for us
+ raise bzrlib.errors.NoRepositoryPresent(repo.bzrdir)
+ except bzrlib.errors.NoRepositoryPresent:
+ # branch
+
+ name = 'master'
+ remote_branch = origin.open_branch()
+
+ if not is_local:
+ peers[name] = remote_branch.base
+ branch = get_remote_branch(origin, remote_branch, name)
+ else:
+ branch = remote_branch
+
+ branches[name] = branch.base
+
+ return branch.repository
else:
- peer = None
+ # repository
- return branch
+ wanted = get_config('remote-bzr.branches').rstrip().split(', ')
+ # stupid python
+ wanted = [e for e in wanted if e]
+
+ for name, remote_branch in find_branches(repo, wanted):
+
+ if not is_local:
+ peers[name] = remote_branch.base
+ branch = get_remote_branch(origin, remote_branch, name)
+ else:
+ branch = remote_branch
+
+ branches[name] = branch.base
+
+ return repo
+
+def fix_path(alias, orig_url):
+ url = urlparse.urlparse(orig_url, 'file')
+ if url.scheme != 'file' or os.path.isabs(url.path):
+ return
+ abs_url = urlparse.urljoin("%s/" % os.getcwd(), orig_url)
+ cmd = ['git', 'config', 'remote.%s.url' % alias, "bzr::%s" % abs_url]
+ subprocess.call(cmd)
def main(args):
- global marks, prefix, dirname
+ global marks, prefix, gitdir, dirname
global tags, filenodes
global blob_marks
global parsed_refs
global files_cache
+ global is_tmp
+ global branches, peers
alias = args[1]
url = args[2]
- prefix = 'refs/bzr/%s' % alias
tags = {}
filenodes = {}
blob_marks = {}
parsed_refs = {}
files_cache = {}
+ marks = None
+ branches = {}
+ peers = {}
+
+ if alias[5:] == url:
+ is_tmp = True
+ alias = hashlib.sha1(alias).hexdigest()
+ else:
+ is_tmp = False
+ prefix = 'refs/bzr/%s' % alias
gitdir = os.environ['GIT_DIR']
dirname = os.path.join(gitdir, 'bzr', alias)
+ if not is_tmp:
+ fix_path(alias, url)
+
if not os.path.exists(dirname):
os.makedirs(dirname)
+ if hasattr(bzrlib.ui.ui_factory, 'be_quiet'):
+ bzrlib.ui.ui_factory.be_quiet(True)
+
repo = get_repo(url, alias)
marks_path = os.path.join(dirname, 'marks-int')
die('unhandled command: %s' % line)
sys.stdout.flush()
- marks.store()
+def bye():
+ if not marks:
+ return
+ if not is_tmp:
+ marks.store()
+ else:
+ shutil.rmtree(dirname)
+atexit.register(bye)
sys.exit(main(sys.argv))