diff --git a/dulwich/client.py b/dulwich/client.py index b13427a6..2c8b6aaf 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1711 +1,1722 @@ # client.py -- Implementation of the client side git protocols # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Client side support for the Git protocol. The Dulwich client supports the following capabilities: * thin-pack * multi_ack_detailed * multi_ack * side-band-64k * ofs-delta * quiet * report-status * delete-refs Known capabilities that are not supported: * shallow * no-progress * include-tag """ from contextlib import closing from io import BytesIO, BufferedReader import select import socket import subprocess import sys try: from urllib import quote as urlquote from urllib import unquote as urlunquote except ImportError: from urllib.parse import quote as urlquote from urllib.parse import unquote as urlunquote try: import urlparse except ImportError: import urllib.parse as urlparse import dulwich from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, UpdateRefsError, ) from dulwich.protocol import ( HangupException, _RBUFSIZE, agent_string, capability_agent, extract_capability_names, CAPABILITY_AGENT, CAPABILITY_DELETE_REFS, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, CAPABILITY_SHALLOW, CAPABILITY_SYMREF, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITIES_REF, KNOWN_RECEIVE_CAPABILITIES, KNOWN_UPLOAD_CAPABILITIES, COMMAND_DEEPEN, COMMAND_DONE, COMMAND_HAVE, COMMAND_WANT, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, PktLineParser, Protocol, ProtocolFile, TCP_GIT_PORT, ZERO_SHA, extract_capabilities, parse_capability, ) from dulwich.pack import ( write_pack_data, write_pack_objects, ) from dulwich.refs import ( read_info_refs, ANNOTATED_TAG_SUFFIX, ) class InvalidWants(Exception): """Invalid wants.""" def __init__(self, wants): Exception.__init__( self, "requested wants not in server provided refs: %r" % wants) def _fileno_can_read(fileno): """Check if a file descriptor is readable.""" return len(select.select([fileno], [], [], 0)[0]) > 0 def _win32_peek_avail(handle): """Wrapper around PeekNamedPipe to check how many bytes are available.""" from ctypes import byref, wintypes, windll c_avail = wintypes.DWORD() c_message = wintypes.DWORD() success = windll.kernel32.PeekNamedPipe( handle, None, 0, None, byref(c_avail), byref(c_message)) if not success: raise OSError(wintypes.GetLastError()) return c_avail.value COMMON_CAPABILITIES = [CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K] UPLOAD_CAPABILITIES = ([CAPABILITY_THIN_PACK, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_SHALLOW] + COMMON_CAPABILITIES) RECEIVE_CAPABILITIES = [CAPABILITY_REPORT_STATUS] + COMMON_CAPABILITIES class ReportStatusParser(object): """Handle status as reported by servers with 'report-status' capability. """ def __init__(self): self._done = False self._pack_status = None self._ref_status_ok = True self._ref_statuses = [] def check(self): """Check if there were any errors and, if so, raise exceptions. :raise SendPackError: Raised when the server could not unpack :raise UpdateRefsError: Raised when refs could not be updated """ if self._pack_status not in (b'unpack ok', None): raise SendPackError(self._pack_status) if not self._ref_status_ok: ref_status = {} ok = set() for status in self._ref_statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status # TODO(jelmer): don't assume encoding of refs is ascii. raise UpdateRefsError(', '.join([ refname.decode('ascii') for refname in ref_status if refname not in ok]) + ' failed to update', ref_status=ref_status) def handle_packet(self, pkt): """Handle a packet. :raise GitProtocolError: Raised when packets are received after a flush packet. """ if self._done: raise GitProtocolError("received more data after status report") if pkt is None: self._done = True return if self._pack_status is None: self._pack_status = pkt.strip() else: ref_status = pkt.strip() self._ref_statuses.append(ref_status) if not ref_status.startswith(b'ok '): self._ref_status_ok = False def read_pkt_refs(proto): server_capabilities = None refs = {} # Receive refs from server for pkt in proto.read_pkt_seq(): (sha, ref) = pkt.rstrip(b'\n').split(None, 1) if sha == b'ERR': raise GitProtocolError(ref.decode('utf-8', 'replace')) if server_capabilities is None: (ref, server_capabilities) = extract_capabilities(ref) refs[ref] = sha if len(refs) == 0: return {}, set([]) if refs == {CAPABILITIES_REF: ZERO_SHA}: refs = {} return refs, set(server_capabilities) class FetchPackResult(object): """Result of a fetch-pack operation. :var refs: Dictionary with all remote refs :var symrefs: Dictionary with remote symrefs :var agent: User agent string """ _FORWARDED_ATTRS = [ 'clear', 'copy', 'fromkeys', 'get', 'has_key', 'items', 'iteritems', 'iterkeys', 'itervalues', 'keys', 'pop', 'popitem', 'setdefault', 'update', 'values', 'viewitems', 'viewkeys', 'viewvalues'] def __init__(self, refs, symrefs, agent): self.refs = refs self.symrefs = symrefs self.agent = agent def _warn_deprecated(self): import warnings warnings.warn( "Use FetchPackResult.refs instead.", DeprecationWarning, stacklevel=3) def __eq__(self, other): if isinstance(other, dict): self._warn_deprecated() return (self.refs == other) return (self.refs == other.refs and self.symrefs == other.symrefs and self.agent == other.agent) def __contains__(self, name): self._warn_deprecated() return name in self.refs def __getitem__(self, name): self._warn_deprecated() return self.refs[name] def __len__(self): self._warn_deprecated() return len(self.refs) def __iter__(self): self._warn_deprecated() return iter(self.refs) def __getattribute__(self, name): if name in type(self)._FORWARDED_ATTRS: self._warn_deprecated() return getattr(self.refs, name) return super(FetchPackResult, self).__getattribute__(name) def __repr__(self): return "%s(%r, %r, %r)" % ( self.__class__.__name__, self.refs, self.symrefs, self.agent) # TODO(durin42): this doesn't correctly degrade if the server doesn't # support some capabilities. This should work properly with servers # that don't support multi_ack. class GitClient(object): """Git smart server client. """ def __init__(self, thin_packs=True, report_activity=None, quiet=False): """Create a new GitClient instance. :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. """ self._report_activity = report_activity self._report_status_parser = None self._fetch_capabilities = set(UPLOAD_CAPABILITIES) self._fetch_capabilities.add(capability_agent()) self._send_capabilities = set(RECEIVE_CAPABILITIES) self._send_capabilities.add(capability_agent()) if quiet: self._send_capabilities.add(CAPABILITY_QUIET) if not thin_packs: self._fetch_capabilities.remove(CAPABILITY_THIN_PACK) def get_url(self, path): """Retrieves full url to given path. :param path: Repository path (as string) :return: Url to path (as string) """ raise NotImplementedError(self.get_url) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): """Create an instance of this client from a urlparse.parsed object. :param parsedurl: Result of urlparse.urlparse() :return: A `GitClient` object """ raise NotImplementedError(cls.from_parsedurl) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of objects and list of pack data to include :param progress: Optional progress function :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ raise NotImplementedError(self.send_pack) def fetch(self, path, target, determine_wants=None, progress=None, depth=None): """Fetch into a target repository. :param path: Path to fetch from (as bytestring) :param target: Target repository to fetch into :param determine_wants: Optional function to determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. :param progress: Optional progress function :param depth: Depth to fetch at :return: Dictionary with all remote refs (not just those fetched) """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all if CAPABILITY_THIN_PACK in self._fetch_capabilities: # TODO(jelmer): Avoid reading entire file into memory and # only processing it after the whole file has been fetched. f = BytesIO() def commit(): if f.tell(): f.seek(0) target.object_store.add_thin_pack(f.read, None) def abort(): pass else: f, commit, abort = target.object_store.add_pack() try: result = self.fetch_pack( path, determine_wants, target.get_graph_walker(), f.write, progress=progress, depth=depth) except BaseException: abort() raise else: commit() return result def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param path: Remote path to fetch from :param determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack :param progress: Callback for progress reports (strings) + :param depth: Shallow fetch depth :return: FetchPackResult object """ raise NotImplementedError(self.fetch_pack) def get_refs(self, path): """Retrieve the current refs from a git smart server. :param path: Path to the repo to fetch from. (as bytestring) """ raise NotImplementedError(self.get_refs) def _parse_status_report(self, proto): unpack = proto.read_pkt_line().strip() if unpack != b'unpack ok': st = True # flush remaining error data while st is not None: st = proto.read_pkt_line() raise SendPackError(unpack) statuses = [] errs = False ref_status = proto.read_pkt_line() while ref_status: ref_status = ref_status.strip() statuses.append(ref_status) if not ref_status.startswith(b'ok '): errs = True ref_status = proto.read_pkt_line() if errs: ref_status = {} ok = set() for status in statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status raise UpdateRefsError(', '.join([ refname for refname in ref_status if refname not in ok]) + b' failed to update', ref_status=ref_status) def _read_side_band64k_data(self, proto, channel_callbacks): """Read per-channel data. This requires the side-band-64k capability. :param proto: Protocol object to read from :param channel_callbacks: Dictionary mapping channels to packet handlers to use. None for a callback discards channel data. """ for pkt in proto.read_pkt_seq(): channel = ord(pkt[:1]) pkt = pkt[1:] try: cb = channel_callbacks[channel] except KeyError: raise AssertionError('Invalid sideband channel %d' % channel) else: if cb is not None: cb(pkt) def _handle_receive_pack_head(self, proto, capabilities, old_refs, new_refs): """Handle the head of a 'git-receive-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param old_refs: Old refs, as received from the server :param new_refs: Refs to change :return: (have, want) tuple """ want = [] have = [x for x in old_refs.values() if not x == ZERO_SHA] sent_capabilities = False for refname in new_refs: if not isinstance(refname, bytes): raise TypeError('refname is not a bytestring: %r' % refname) old_sha1 = old_refs.get(refname, ZERO_SHA) if not isinstance(old_sha1, bytes): raise TypeError('old sha1 for %s is not a bytestring: %r' % (refname, old_sha1)) new_sha1 = new_refs.get(refname, ZERO_SHA) if not isinstance(new_sha1, bytes): raise TypeError('old sha1 for %s is not a bytestring %r' % (refname, new_sha1)) if old_sha1 != new_sha1: if sent_capabilities: proto.write_pkt_line(old_sha1 + b' ' + new_sha1 + b' ' + refname) else: proto.write_pkt_line( old_sha1 + b' ' + new_sha1 + b' ' + refname + b'\0' + b' '.join(capabilities)) sent_capabilities = True if new_sha1 not in have and new_sha1 != ZERO_SHA: want.append(new_sha1) proto.write_pkt_line(None) return (have, want) def _negotiate_receive_pack_capabilities(self, server_capabilities): negotiated_capabilities = ( self._send_capabilities & server_capabilities) unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_RECEIVE_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities return negotiated_capabilities def _handle_receive_pack_tail(self, proto, capabilities, progress=None): """Handle the tail of a 'git-receive-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param progress: Optional progress reporting function """ if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: def progress(x): pass channel_callbacks = {2: progress} if CAPABILITY_REPORT_STATUS in capabilities: channel_callbacks[1] = PktLineParser( self._report_status_parser.handle_packet).parse self._read_side_band64k_data(proto, channel_callbacks) else: if CAPABILITY_REPORT_STATUS in capabilities: for pkt in proto.read_pkt_seq(): self._report_status_parser.handle_packet(pkt) if self._report_status_parser is not None: self._report_status_parser.check() def _negotiate_upload_pack_capabilities(self, server_capabilities): unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_UPLOAD_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities symrefs = {} agent = None for capability in server_capabilities: k, v = parse_capability(capability) if k == CAPABILITY_SYMREF: (src, dst) = v.split(b':', 1) symrefs[src] = dst if k == CAPABILITY_AGENT: agent = v negotiated_capabilities = ( self._fetch_capabilities & server_capabilities) return (negotiated_capabilities, symrefs, agent) def _handle_upload_pack_head(self, proto, capabilities, graph_walker, wants, can_read, depth): """Handle the head of a 'git-upload-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param graph_walker: GraphWalker instance to call .ack() on :param wants: List of commits to fetch :param can_read: function that returns a boolean that indicates whether there is extra graph data to read on proto :param depth: Depth for request """ assert isinstance(wants, list) and isinstance(wants[0], bytes) proto.write_pkt_line(COMMAND_WANT + b' ' + wants[0] + b' ' + b' '.join(capabilities) + b'\n') for want in wants[1:]: proto.write_pkt_line(COMMAND_WANT + b' ' + want + b'\n') + if getattr(graph_walker, 'shallow', None): + if not CAPABILITY_SHALLOW in capabilities: + raise GitProtocolError( + "server does not support shallow capability required for " + "shallow") + for obj_id in graph_walker.shallow: + proto.write_pkt_line(COMMAND_SHALLOW + b' ' + shallow + b'\n') if depth not in (0, None): if not CAPABILITY_SHALLOW in capabilities: raise GitProtocolError( "server does not support shallow capability required for " "depth") proto.write_pkt_line(b'%s %d\n' % (COMMAND_DEEPEN, depth)) proto.write_pkt_line(None) have = next(graph_walker) while have: proto.write_pkt_line(COMMAND_HAVE + b' ' + have + b'\n') if can_read(): pkt = proto.read_pkt_line() parts = pkt.rstrip(b'\n').split(b' ') if parts[0] == b'ACK': graph_walker.ack(parts[1]) if parts[2] in (b'continue', b'common'): pass elif parts[2] == b'ready': break else: raise AssertionError( "%s not in ('continue', 'ready', 'common)" % parts[2]) have = next(graph_walker) proto.write_pkt_line(COMMAND_DONE + b'\n') def _handle_upload_pack_tail(self, proto, capabilities, graph_walker, pack_data, progress=None, rbufsize=_RBUFSIZE): """Handle the tail of a 'git-upload-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param graph_walker: GraphWalker instance to call .ack() on :param pack_data: Function to call with pack data :param progress: Optional progress reporting function :param rbufsize: Read buffer size """ pkt = proto.read_pkt_line() while pkt: parts = pkt.rstrip(b'\n').split(b' ') if parts[0] == b'ACK': graph_walker.ack(parts[1]) if len(parts) < 3 or parts[2] not in ( b'ready', b'continue', b'common'): break pkt = proto.read_pkt_line() if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: # Just ignore progress data def progress(x): pass self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: pack_data, SIDE_BAND_CHANNEL_PROGRESS: progress} ) else: while True: data = proto.read(rbufsize) if data == b"": break pack_data(data) def check_wants(wants, refs): """Check that a set of wants is valid. :param wants: Set of object SHAs to fetch :param refs: Refs dictionary to check against """ missing = set(wants) - { v for (k, v) in refs.items() if not k.endswith(ANNOTATED_TAG_SUFFIX)} if missing: raise InvalidWants(missing) def remote_error_from_stderr(stderr): """Return an appropriate exception based on stderr output. """ if stderr is None: return HangupException() for l in stderr.readlines(): if l.startswith(b'ERROR: '): return GitProtocolError( l[len(b'ERROR: '):].decode('utf-8', 'replace')) return GitProtocolError(l.decode('utf-8', 'replace')) return HangupException() class TraditionalGitClient(GitClient): """Traditional Git client.""" DEFAULT_ENCODING = 'utf-8' def __init__(self, path_encoding=DEFAULT_ENCODING, **kwargs): self._remote_path_encoding = path_encoding super(TraditionalGitClient, self).__init__(**kwargs) def _connect(self, cmd, path): """Create a connection to the server. This method is abstract - concrete implementations should implement their own variant which connects to the server and returns an initialized Protocol object with the service ready for use and a can_read function which may be used to see if reads would block. :param cmd: The git service name to which we should connect. :param path: The path we should pass to the service. (as bytestirng) """ raise NotImplementedError() def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of objects and pack data to upload. :param progress: Optional callback called with progress updates :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ proto, unused_can_read, stderr = self._connect(b'receive-pack', path) with proto: try: old_refs, server_capabilities = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) negotiated_capabilities = \ self._negotiate_receive_pack_capabilities(server_capabilities) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() report_status_parser = self._report_status_parser try: new_refs = orig_new_refs = update_refs(dict(old_refs)) except BaseException: proto.write_pkt_line(None) raise if CAPABILITY_DELETE_REFS not in server_capabilities: # Server does not support deletions. Fail later. new_refs = dict(orig_new_refs) for ref, sha in orig_new_refs.items(): if sha == ZERO_SHA: if CAPABILITY_REPORT_STATUS in negotiated_capabilities: report_status_parser._ref_statuses.append( b'ng ' + sha + b' remote does not support deleting refs') report_status_parser._ref_status_ok = False del new_refs[ref] if new_refs is None: proto.write_pkt_line(None) return old_refs if len(new_refs) == 0 and len(orig_new_refs): # NOOP - Original new refs filtered out by policy proto.write_pkt_line(None) if report_status_parser is not None: report_status_parser.check() return old_refs (have, want) = self._handle_receive_pack_head( proto, negotiated_capabilities, old_refs, new_refs) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) dowrite = bool(pack_data_count) dowrite = dowrite or any(old_refs.get(ref) != sha for (ref, sha) in new_refs.items() if sha != ZERO_SHA) if dowrite: write_pack_data(proto.write_file(), pack_data_count, pack_data) self._handle_receive_pack_tail( proto, negotiated_capabilities, progress) return new_refs def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - depth=None, progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param path: Remote path to fetch from :param determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack - :param depth: Depth for request :param progress: Callback for progress reports (strings) + :param depth: Shallow fetch depth :return: FetchPackResult object """ proto, can_read, stderr = self._connect(b'upload-pack', path) with proto: try: refs, server_capabilities = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) if refs is None: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) try: wants = determine_wants(refs) except BaseException: proto.write_pkt_line(None) raise if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) check_wants(wants, refs) self._handle_upload_pack_head( proto, negotiated_capabilities, graph_walker, wants, can_read, depth=depth) self._handle_upload_pack_tail( proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult(refs, symrefs, agent) def get_refs(self, path): """Retrieve the current refs from a git smart server.""" # stock `git ls-remote` uses upload-pack proto, _, stderr = self._connect(b'upload-pack', path) with proto: try: refs, _ = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) proto.write_pkt_line(None) return refs def archive(self, path, committish, write_data, progress=None, write_error=None, format=None, subdirs=None, prefix=None): proto, can_read, stderr = self._connect(b'upload-archive', path) with proto: if format is not None: proto.write_pkt_line(b"argument --format=" + format) proto.write_pkt_line(b"argument " + committish) if subdirs is not None: for subdir in subdirs: proto.write_pkt_line(b"argument " + subdir) if prefix is not None: proto.write_pkt_line(b"argument --prefix=" + prefix) proto.write_pkt_line(None) try: pkt = proto.read_pkt_line() except HangupException: raise remote_error_from_stderr(stderr) if pkt == b"NACK\n": return elif pkt == b"ACK\n": pass elif pkt.startswith(b"ERR "): raise GitProtocolError( pkt[4:].rstrip(b"\n").decode('utf-8', 'replace')) else: raise AssertionError("invalid response %r" % pkt) ret = proto.read_pkt_line() if ret is not None: raise AssertionError("expected pkt tail") self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: write_data, SIDE_BAND_CHANNEL_PROGRESS: progress, SIDE_BAND_CHANNEL_FATAL: write_error}) class TCPGitClient(TraditionalGitClient): """A Git Client that works over TCP directly (i.e. git://).""" def __init__(self, host, port=None, **kwargs): if port is None: port = TCP_GIT_PORT self._host = host self._port = port super(TCPGitClient, self).__init__(**kwargs) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(parsedurl.hostname, port=parsedurl.port, **kwargs) def get_url(self, path): netloc = self._host if self._port is not None and self._port != TCP_GIT_PORT: netloc += ":%d" % self._port return urlparse.urlunsplit(("git", netloc, path, '', '')) def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if not isinstance(path, bytes): path = path.encode(self._remote_path_encoding) sockaddrs = socket.getaddrinfo( self._host, self._port, socket.AF_UNSPEC, socket.SOCK_STREAM) s = None err = socket.error("no address found for %s" % self._host) for (family, socktype, proto, canonname, sockaddr) in sockaddrs: s = socket.socket(family, socktype, proto) s.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1) try: s.connect(sockaddr) break except socket.error as e: err = e if s is not None: s.close() s = None if s is None: raise err # -1 means system default buffering rfile = s.makefile('rb', -1) # 0 means unbuffered wfile = s.makefile('wb', 0) def close(): rfile.close() wfile.close() s.close() proto = Protocol(rfile.read, wfile.write, close, report_activity=self._report_activity) if path.startswith(b"/~"): path = path[1:] # TODO(jelmer): Alternative to ascii? proto.send_cmd( b'git-' + cmd, path, b'host=' + self._host.encode('ascii')) return proto, lambda: _fileno_can_read(s), None class SubprocessWrapper(object): """A socket-like object that talks to a subprocess via pipes.""" def __init__(self, proc): self.proc = proc if sys.version_info[0] == 2: self.read = proc.stdout.read else: self.read = BufferedReader(proc.stdout).read self.write = proc.stdin.write @property def stderr(self): return self.proc.stderr def can_read(self): if sys.platform == 'win32': from msvcrt import get_osfhandle handle = get_osfhandle(self.proc.stdout.fileno()) return _win32_peek_avail(handle) != 0 else: return _fileno_can_read(self.proc.stdout.fileno()) def close(self): self.proc.stdin.close() self.proc.stdout.close() if self.proc.stderr: self.proc.stderr.close() self.proc.wait() def find_git_command(): """Find command to run for system Git (usually C Git). """ if sys.platform == 'win32': # support .exe, .bat and .cmd try: # to avoid overhead import win32api except ImportError: # run through cmd.exe with some overhead return ['cmd', '/c', 'git'] else: status, git = win32api.FindExecutable('git') return [git] else: return ['git'] class SubprocessGitClient(TraditionalGitClient): """Git client that talks to a server using a subprocess.""" @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) git_command = None def _connect(self, service, path): if not isinstance(service, bytes): raise TypeError(service) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if self.git_command is None: git_command = find_git_command() argv = git_command + [service.decode('ascii'), path] p = subprocess.Popen(argv, bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) pw = SubprocessWrapper(p) return (Protocol(pw.read, pw.write, pw.close, report_activity=self._report_activity), pw.can_read, p.stderr) class LocalGitClient(GitClient): """Git Client that just uses a local Repo.""" def __init__(self, thin_packs=True, report_activity=None, config=None): """Create a new LocalGitClient instance. :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. """ self._report_activity = report_activity # Ignore the thin_packs argument def get_url(self, path): return urlparse.urlunsplit(('file', '', path, '', '')) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) @classmethod def _open_repo(cls, path): from dulwich.repo import Repo if not isinstance(path, str): path = path.decode(sys.getfilesystemencoding()) return closing(Repo(path)) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of items and pack data to upload. :param progress: Optional progress function :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ if not progress: def progress(x): pass with self._open_repo(path) as target: old_refs = target.get_refs() new_refs = update_refs(dict(old_refs)) have = [sha1 for sha1 in old_refs.values() if sha1 != ZERO_SHA] want = [] for refname, new_sha1 in new_refs.items(): if (new_sha1 not in have and new_sha1 not in want and new_sha1 != ZERO_SHA): want.append(new_sha1) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs target.object_store.add_pack_data( *generate_pack_data(have, want, ofs_delta=True)) for refname, new_sha1 in new_refs.items(): old_sha1 = old_refs.get(refname, ZERO_SHA) if new_sha1 != ZERO_SHA: if not target.refs.set_if_equals( refname, old_sha1, new_sha1): progress('unable to set %s to %s' % (refname, new_sha1)) else: if not target.refs.remove_if_equals(refname, old_sha1): progress('unable to remove %s' % refname) return new_refs - def fetch(self, path, target, determine_wants=None, progress=None): + def fetch(self, path, target, determine_wants=None, progress=None, + depth=None): """Fetch into a target repository. :param path: Path to fetch from (as bytestring) :param target: Target repository to fetch into :param determine_wants: Optional function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. :param progress: Optional progress function + :param depth: Shallow fetch depth :return: FetchPackResult object """ with self._open_repo(path) as r: refs = r.fetch(target, determine_wants=determine_wants, - progress=progress) + progress=progress, depth=depth) return FetchPackResult(refs, r.refs.get_symrefs(), agent_string()) def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param path: Remote path to fetch from :param determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack :param progress: Callback for progress reports (strings) + :param depth: Shallow fetch depth :return: FetchPackResult object """ with self._open_repo(path) as r: objects_iter = r.fetch_objects( - determine_wants, graph_walker, progress) + determine_wants, graph_walker, progress=progress, depth=depth) symrefs = r.refs.get_symrefs() agent = agent_string() # Did the process short-circuit (e.g. in a stateless RPC call)? # Note that the client still expects a 0-object pack in most cases. if objects_iter is None: return FetchPackResult(None, symrefs, agent) protocol = ProtocolFile(None, pack_data) write_pack_objects(protocol, objects_iter) return FetchPackResult(r.get_refs(), symrefs, agent) def get_refs(self, path): """Retrieve the current refs from a git smart server.""" with self._open_repo(path) as target: return target.get_refs() # What Git client to use for local access default_local_git_client_cls = LocalGitClient class SSHVendor(object): """A client side SSH implementation.""" def connect_ssh(self, host, command, username=None, port=None, password=None, key_filename=None): # This function was deprecated in 0.9.1 import warnings warnings.warn( "SSHVendor.connect_ssh has been renamed to SSHVendor.run_command", DeprecationWarning) return self.run_command(host, command, username=username, port=port, password=password, key_filename=key_filename) def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): """Connect to an SSH server. Run a command remotely and return a file-like object for interaction with the remote command. :param host: Host name :param command: Command to run (as argv array) :param username: Optional ame of user to log in as :param port: Optional SSH port to use :param password: Optional ssh password for login or private key :param key_filename: Optional path to private keyfile """ raise NotImplementedError(self.run_command) class StrangeHostname(Exception): """Refusing to connect to strange SSH hostname.""" def __init__(self, hostname): super(StrangeHostname, self).__init__(hostname) class SubprocessSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'ssh' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if password is not None: raise NotImplementedError( "Setting password not supported by SubprocessSSHVendor.") args = ['ssh', '-x'] if port: args.extend(['-p', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return SubprocessWrapper(proc) class PLinkSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'plink' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if sys.platform == 'win32': args = ['plink.exe', '-ssh'] else: args = ['plink', '-ssh'] if password is not None: import warnings warnings.warn( "Invoking PLink with a password exposes the password in the " "process list.") args.extend(['-pw', str(password)]) if port: args.extend(['-P', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return SubprocessWrapper(proc) def ParamikoSSHVendor(**kwargs): import warnings warnings.warn( "ParamikoSSHVendor has been moved to dulwich.contrib.paramiko_vendor.", DeprecationWarning) from dulwich.contrib.paramiko_vendor import ParamikoSSHVendor return ParamikoSSHVendor(**kwargs) # Can be overridden by users get_ssh_vendor = SubprocessSSHVendor class SSHGitClient(TraditionalGitClient): def __init__(self, host, port=None, username=None, vendor=None, config=None, password=None, key_filename=None, **kwargs): self.host = host self.port = port self.username = username self.password = password self.key_filename = key_filename super(SSHGitClient, self).__init__(**kwargs) self.alternative_paths = {} if vendor is not None: self.ssh_vendor = vendor else: self.ssh_vendor = get_ssh_vendor() def get_url(self, path): netloc = self.host if self.port is not None: netloc += ":%d" % self.port if self.username is not None: netloc = urlquote(self.username, '@/:') + "@" + netloc return urlparse.urlunsplit(('ssh', netloc, path, '', '')) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(host=parsedurl.hostname, port=parsedurl.port, username=parsedurl.username, **kwargs) def _get_cmd_path(self, cmd): cmd = self.alternative_paths.get(cmd, b'git-' + cmd) assert isinstance(cmd, bytes) return cmd def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if path.startswith("/~"): path = path[1:] argv = (self._get_cmd_path(cmd).decode(self._remote_path_encoding) + " '" + path + "'") kwargs = {} if self.password is not None: kwargs['password'] = self.password if self.key_filename is not None: kwargs['key_filename'] = self.key_filename con = self.ssh_vendor.run_command( self.host, argv, port=self.port, username=self.username, **kwargs) return (Protocol(con.read, con.write, con.close, report_activity=self._report_activity), con.can_read, getattr(con, 'stderr', None)) def default_user_agent_string(): # Start user agent with "git/", because GitHub requires this. :-( See # https://github.com/jelmer/dulwich/issues/562 for details. return "git/dulwich/%s" % ".".join([str(x) for x in dulwich.__version__]) def default_urllib3_manager(config, **override_kwargs): """Return `urllib3` connection pool manager. Honour detected proxy configurations. :param config: `dulwich.config.ConfigDict` instance with Git configuration. :param kwargs: Additional arguments for urllib3.ProxyManager :return: `urllib3.ProxyManager` instance for proxy configurations, `urllib3.PoolManager` otherwise. """ proxy_server = user_agent = None ca_certs = ssl_verify = None if config is not None: try: proxy_server = config.get(b"http", b"proxy") except KeyError: pass try: user_agent = config.get(b"http", b"useragent") except KeyError: pass # TODO(jelmer): Support per-host settings try: ssl_verify = config.get_boolean(b"http", b"sslVerify") except KeyError: ssl_verify = True try: ca_certs = config.get_boolean(b"http", b"sslCAInfo") except KeyError: ca_certs = None if user_agent is None: user_agent = default_user_agent_string() headers = {"User-agent": user_agent} kwargs = {} if ssl_verify is True: kwargs['cert_reqs'] = "CERT_REQUIRED" elif ssl_verify is False: kwargs['cert_reqs'] = 'CERT_NONE' else: # Default to SSL verification kwargs['cert_reqs'] = "CERT_REQUIRED" if ca_certs is not None: kwargs['ca_certs'] = ca_certs kwargs.update(override_kwargs) # Try really hard to find a SSL certificate path if 'ca_certs' not in kwargs and kwargs.get('cert_reqs') != 'CERT_NONE': try: import certifi except ImportError: pass else: kwargs['ca_certs'] = certifi.where() import urllib3 if proxy_server is not None: # `urllib3` requires a `str` object in both Python 2 and 3, while # `ConfigDict` coerces entries to `bytes` on Python 3. Compensate. if not isinstance(proxy_server, str): proxy_server = proxy_server.decode() manager = urllib3.ProxyManager(proxy_server, headers=headers, **kwargs) else: manager = urllib3.PoolManager(headers=headers, **kwargs) return manager class HttpGitClient(GitClient): def __init__(self, base_url, dumb=None, pool_manager=None, config=None, username=None, password=None, **kwargs): self._base_url = base_url.rstrip("/") + "/" self._username = username self._password = password self.dumb = dumb if pool_manager is None: self.pool_manager = default_urllib3_manager(config) else: self.pool_manager = pool_manager if username is not None: # No escaping needed: ":" is not allowed in username: # https://tools.ietf.org/html/rfc2617#section-2 credentials = "%s:%s" % (username, password) import urllib3.util basic_auth = urllib3.util.make_headers(basic_auth=credentials) self.pool_manager.headers.update(basic_auth) GitClient.__init__(self, **kwargs) def get_url(self, path): return self._get_url(path).rstrip("/") @classmethod def from_parsedurl(cls, parsedurl, **kwargs): password = parsedurl.password if password is not None: kwargs['password'] = urlunquote(password) username = parsedurl.username if username is not None: kwargs['username'] = urlunquote(username) # TODO(jelmer): This also strips the username parsedurl = parsedurl._replace(netloc=parsedurl.hostname) return cls(urlparse.urlunparse(parsedurl), **kwargs) def __repr__(self): return "%s(%r, dumb=%r)" % ( type(self).__name__, self._base_url, self.dumb) def _get_url(self, path): if not isinstance(path, str): # TODO(jelmer): this is unrelated to the local filesystem; # This is not necessarily the right encoding to decode the path # with. path = path.decode(sys.getfilesystemencoding()) return urlparse.urljoin(self._base_url, path).rstrip("/") + "/" def _http_request(self, url, headers=None, data=None, allow_compression=False): """Perform HTTP request. :param url: Request URL. :param headers: Optional custom headers to override defaults. :param data: Request data. :param allow_compression: Allow GZipped communication. :return: Tuple (`response`, `read`), where response is an `urllib3` response object with additional `content_type` and `redirect_location` properties, and `read` is a consumable read method for the response data. """ req_headers = self.pool_manager.headers.copy() if headers is not None: req_headers.update(headers) req_headers["Pragma"] = "no-cache" if allow_compression: req_headers["Accept-Encoding"] = "gzip" else: req_headers["Accept-Encoding"] = "identity" if data is None: resp = self.pool_manager.request("GET", url, headers=req_headers) else: resp = self.pool_manager.request("POST", url, headers=req_headers, body=data) if resp.status == 404: raise NotGitRepository() elif resp.status != 200: raise GitProtocolError("unexpected http resp %d for %s" % (resp.status, url)) # TODO: Optimization available by adding `preload_content=False` to the # request and just passing the `read` method on instead of going via # `BytesIO`, if we can guarantee that the entire response is consumed # before issuing the next to still allow for connection reuse from the # pool. read = BytesIO(resp.data).read resp.content_type = resp.getheader("Content-Type") resp.redirect_location = resp.get_redirect_location() return resp, read def _discover_references(self, service, base_url): assert base_url[-1] == "/" tail = "info/refs" headers = {"Accept": "*/*"} if self.dumb is not True: tail += "?service=%s" % service.decode('ascii') url = urlparse.urljoin(base_url, tail) resp, read = self._http_request(url, headers, allow_compression=True) if resp.redirect_location: # Something changed (redirect!), so let's update the base URL if not resp.redirect_location.endswith(tail): raise GitProtocolError( "Redirected from URL %s to URL %s without %s" % ( url, resp.redirect_location, tail)) base_url = resp.redirect_location[:-len(tail)] try: self.dumb = not resp.content_type.startswith("application/x-git-") if not self.dumb: proto = Protocol(read, None) # The first line should mention the service try: [pkt] = list(proto.read_pkt_seq()) except ValueError: raise GitProtocolError( "unexpected number of packets received") if pkt.rstrip(b'\n') != (b'# service=' + service): raise GitProtocolError( "unexpected first line %r from smart server" % pkt) return read_pkt_refs(proto) + (base_url, ) else: return read_info_refs(resp), set(), base_url finally: resp.close() def _smart_request(self, service, url, data): assert url[-1] == "/" url = urlparse.urljoin(url, service) result_content_type = "application/x-%s-result" % service headers = { "Content-Type": "application/x-%s-request" % service, "Accept": result_content_type, "Content-Length": str(len(data)), } resp, read = self._http_request(url, headers, data) if resp.content_type != result_content_type: raise GitProtocolError("Invalid content-type from server: %s" % resp.content_type) return resp, read def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of elements and pack data to upload. :param progress: Optional progress function :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ url = self._get_url(path) old_refs, server_capabilities, url = self._discover_references( b"git-receive-pack", url) negotiated_capabilities = self._negotiate_receive_pack_capabilities( server_capabilities) negotiated_capabilities.add(capability_agent()) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() new_refs = update_refs(dict(old_refs)) if new_refs is None: # Determine wants function is aborting the push. return old_refs if self.dumb: raise NotImplementedError(self.fetch_pack) req_data = BytesIO() req_proto = Protocol(None, req_data.write) (have, want) = self._handle_receive_pack_head( req_proto, negotiated_capabilities, old_refs, new_refs) if not want and set(new_refs.items()).issubset(set(old_refs.items())): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) if pack_data_count: write_pack_data(req_proto.write_file(), pack_data_count, pack_data) resp, read = self._smart_request("git-receive-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) self._handle_receive_pack_tail( resp_proto, negotiated_capabilities, progress) return new_refs finally: resp.close() def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - depth=None, progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param determine_wants: Callback that returns list of commits to fetch :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack :param progress: Callback for progress reports (strings) :param depth: Depth for request :return: FetchPackResult object """ url = self._get_url(path) refs, server_capabilities, url = self._discover_references( b"git-upload-pack", url) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) wants = determine_wants(refs) if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: return FetchPackResult(refs, symrefs, agent) if self.dumb: raise NotImplementedError(self.send_pack) check_wants(wants, refs) req_data = BytesIO() req_proto = Protocol(None, req_data.write) self._handle_upload_pack_head( req_proto, negotiated_capabilities, graph_walker, wants, lambda: False, depth=depth) resp, read = self._smart_request( "git-upload-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) self._handle_upload_pack_tail( resp_proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult(refs, symrefs, agent) finally: resp.close() def get_refs(self, path): """Retrieve the current refs from a git smart server.""" url = self._get_url(path) refs, _, _ = self._discover_references( b"git-upload-pack", url) return refs def get_transport_and_path_from_url(url, config=None, **kwargs): """Obtain a git client from a URL. :param url: URL to open (a unicode string) :param config: Optional config object :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. :return: Tuple with client instance and relative path. """ parsed = urlparse.urlparse(url) if parsed.scheme == 'git': return (TCPGitClient.from_parsedurl(parsed, **kwargs), parsed.path) elif parsed.scheme in ('git+ssh', 'ssh'): return SSHGitClient.from_parsedurl(parsed, **kwargs), parsed.path elif parsed.scheme in ('http', 'https'): return HttpGitClient.from_parsedurl( parsed, config=config, **kwargs), parsed.path elif parsed.scheme == 'file': return default_local_git_client_cls.from_parsedurl( parsed, **kwargs), parsed.path raise ValueError("unknown scheme '%s'" % parsed.scheme) def parse_rsync_url(location): """Parse a rsync-style URL.""" if ':' in location and '@' not in location: # SSH with no user@, zero or one leading slash. (host, path) = location.split(':', 1) user = None elif ':' in location: # SSH with user@host:foo. user_host, path = location.split(':', 1) if '@' in user_host: user, host = user_host.rsplit('@', 1) else: user = None host = user_host else: raise ValueError('not a valid rsync-style URL') return (user, host, path) def get_transport_and_path(location, **kwargs): """Obtain a git client from a URL. :param location: URL or path (a string) :param config: Optional config object :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. :return: Tuple with client instance and relative path. """ # First, try to parse it as a URL try: return get_transport_and_path_from_url(location, **kwargs) except ValueError: pass if (sys.platform == 'win32' and location[0].isalpha() and location[1:3] == ':\\'): # Windows local path return default_local_git_client_cls(**kwargs), location try: (username, hostname, path) = parse_rsync_url(location) except ValueError: # Otherwise, assume it's a local path. return default_local_git_client_cls(**kwargs), location else: return SSHGitClient(hostname, username=username, **kwargs), path diff --git a/dulwich/object_store.py b/dulwich/object_store.py index d77f5ac0..8534d621 100644 --- a/dulwich/object_store.py +++ b/dulwich/object_store.py @@ -1,1330 +1,1334 @@ # object_store.py -- Object store for git objects # Copyright (C) 2008-2013 Jelmer Vernooij # and others # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Git object store interfaces and implementation.""" from io import BytesIO import errno from itertools import chain import os import stat import sys import tempfile import time from dulwich.diff_tree import ( tree_changes, walk_trees, ) from dulwich.errors import ( NotTreeError, ) from dulwich.file import GitFile from dulwich.objects import ( Commit, ShaFile, Tag, Tree, ZERO_SHA, hex_to_sha, sha_to_hex, hex_to_filename, S_ISGITLINK, object_class, ) from dulwich.pack import ( Pack, PackData, PackInflater, iter_sha1, pack_objects_to_data, write_pack_header, write_pack_index_v2, write_pack_data, write_pack_object, compute_file_sha, PackIndexer, PackStreamCopier, ) from dulwich.refs import ANNOTATED_TAG_SUFFIX INFODIR = 'info' PACKDIR = 'pack' class BaseObjectStore(object): """Object store interface.""" def determine_wants_all(self, refs): return [sha for (ref, sha) in refs.items() if sha not in self and not ref.endswith(ANNOTATED_TAG_SUFFIX) and not sha == ZERO_SHA] def iter_shas(self, shas): """Iterate over the objects for the specified shas. :param shas: Iterable object with SHAs :return: Object iterator """ return ObjectStoreIterator(self, shas) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" raise NotImplementedError(self.contains_loose) def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" raise NotImplementedError(self.contains_packed) def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ return self.contains_packed(sha) or self.contains_loose(sha) @property def packs(self): """Iterable of pack objects.""" raise NotImplementedError def get_raw(self, name): """Obtain the raw text for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ raise NotImplementedError(self.get_raw) def __getitem__(self, sha): """Obtain an object by SHA1.""" type_num, uncomp = self.get_raw(sha) return ShaFile.from_raw_string(type_num, uncomp, sha=sha) def __iter__(self): """Iterate over the SHAs that are present in this store.""" raise NotImplementedError(self.__iter__) def add_object(self, obj): """Add a single object to this object store. """ raise NotImplementedError(self.add_object) def add_objects(self, objects, progress=None): """Add a set of objects to this object store. :param objects: Iterable over a list of (object, path) tuples """ raise NotImplementedError(self.add_objects) def add_pack_data(self, count, pack_data, progress=None): """Add pack data to this object store. :param num_items: Number of items to add :param pack_data: Iterator over pack data tuples """ if count == 0: # Don't bother writing an empty pack file return f, commit, abort = self.add_pack() try: write_pack_data(f, count, pack_data, progress) except BaseException: abort() raise else: return commit() def tree_changes(self, source, target, want_unchanged=False, include_trees=False, change_type_same=False): """Find the differences between the contents of two trees :param source: SHA1 of the source tree :param target: SHA1 of the target tree :param want_unchanged: Whether unchanged files should be reported :param include_trees: Whether to include trees :param change_type_same: Whether to report files changing type in the same entry. :return: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ for change in tree_changes(self, source, target, want_unchanged=want_unchanged, include_trees=include_trees, change_type_same=change_type_same): yield ((change.old.path, change.new.path), (change.old.mode, change.new.mode), (change.old.sha, change.new.sha)) def iter_tree_contents(self, tree_id, include_trees=False): """Iterate the contents of a tree and all subtrees. Iteration is depth-first pre-order, as in e.g. os.walk. :param tree_id: SHA1 of the tree. :param include_trees: If True, include tree objects in the iteration. :return: Iterator over TreeEntry namedtuples for all the objects in a tree. """ for entry, _ in walk_trees(self, tree_id, None): if ((entry.mode is not None and not stat.S_ISDIR(entry.mode)) or include_trees): yield entry def find_missing_objects(self, haves, wants, progress=None, get_tagged=None, - get_parents=lambda commit: commit.parents): + get_parents=lambda commit: commit.parents, + depth=None): """Find the missing objects required for a set of revisions. :param haves: Iterable over SHAs already in common. :param wants: Iterable over SHAs of objects to fetch. :param progress: Simple progress function that will be called with updated progress strings. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. :param get_parents: Optional function for getting the parents of a commit. :return: Iterator over (sha, path) pairs. """ finder = MissingObjectFinder(self, haves, wants, progress, get_tagged, get_parents=get_parents) return iter(finder.next, None) def find_common_revisions(self, graphwalker): """Find which revisions this store has in common using graphwalker. :param graphwalker: A graphwalker object. :return: List of SHAs that are in common """ haves = [] sha = next(graphwalker) while sha: if sha in self: haves.append(sha) graphwalker.ack(sha) sha = next(graphwalker) return haves def generate_pack_contents(self, have, want, progress=None): """Iterate over the contents of a pack file. :param have: List of SHA1s of objects that should not be sent :param want: List of SHA1s of objects that should be sent :param progress: Optional progress reporting method """ return self.iter_shas(self.find_missing_objects(have, want, progress)) def generate_pack_data(self, have, want, progress=None, ofs_delta=True): """Generate pack data objects for a set of wants/haves. :param have: List of SHA1s of objects that should not be sent :param want: List of SHA1s of objects that should be sent :param ofs_delta: Whether OFS deltas can be included :param progress: Optional progress reporting method """ # TODO(jelmer): More efficient implementation return pack_objects_to_data( self.generate_pack_contents(have, want, progress)) def peel_sha(self, sha): """Peel all tags from a SHA. :param sha: The object SHA to peel. :return: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ obj = self[sha] obj_class = object_class(obj.type_name) while obj_class is Tag: obj_class, sha = obj.object obj = self[sha] return obj def _collect_ancestors(self, heads, common=set(), get_parents=lambda commit: commit.parents): """Collect all ancestors of heads up to (excluding) those in common. :param heads: commits to start from :param common: commits to end at, or empty set to walk repository completely :param get_parents: Optional function for getting the parents of a commit. :return: a tuple (A, B) where A - all commits reachable from heads but not present in common, B - common (shared) elements that are directly reachable from heads """ bases = set() commits = set() queue = [] queue.extend(heads) while queue: e = queue.pop(0) if e in common: bases.add(e) elif e not in commits: commits.add(e) cmt = self[e] queue.extend(get_parents(cmt)) return (commits, bases) def close(self): """Close any files opened by this object store.""" # Default implementation is a NO-OP class PackBasedObjectStore(BaseObjectStore): def __init__(self): self._pack_cache = {} @property def alternates(self): return [] def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed. This does not check alternates. """ for pack in self.packs: if sha in pack: return True return False def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ if self.contains_packed(sha) or self.contains_loose(sha): return True for alternate in self.alternates: if sha in alternate: return True return False def _pack_cache_stale(self): """Check whether the pack cache is stale.""" raise NotImplementedError(self._pack_cache_stale) def _add_known_pack(self, base_name, pack): """Add a newly appeared pack to the cache by path. """ prev_pack = self._pack_cache.get(base_name) if prev_pack is not pack: self._pack_cache[base_name] = pack if prev_pack: prev_pack.close() def _flush_pack_cache(self): pack_cache = self._pack_cache self._pack_cache = {} while pack_cache: (name, pack) = pack_cache.popitem() pack.close() def close(self): self._flush_pack_cache() @property def packs(self): """List with pack objects.""" if self._pack_cache is None or self._pack_cache_stale(): self._update_pack_cache() return self._pack_cache.values() def _iter_alternate_objects(self): """Iterate over the SHAs of all the objects in alternate stores.""" for alternate in self.alternates: for alternate_object in alternate: yield alternate_object def _iter_loose_objects(self): """Iterate over the SHAs of all loose objects.""" raise NotImplementedError(self._iter_loose_objects) def _get_loose_object(self, sha): raise NotImplementedError(self._get_loose_object) def _remove_loose_object(self, sha): raise NotImplementedError(self._remove_loose_object) def _remove_pack(self, name): raise NotImplementedError(self._remove_pack) def pack_loose_objects(self): """Pack loose objects. :return: Number of objects packed """ objects = set() for sha in self._iter_loose_objects(): objects.add((self._get_loose_object(sha), None)) self.add_objects(list(objects)) for obj, path in objects: self._remove_loose_object(obj.id) return len(objects) def repack(self): """Repack the packs in this repository. Note that this implementation is fairly naive and currently keeps all objects in memory while it repacks. """ loose_objects = set() for sha in self._iter_loose_objects(): loose_objects.add(self._get_loose_object(sha)) objects = {(obj, None) for obj in loose_objects} old_packs = {p.name(): p for p in self.packs} for name, pack in old_packs.items(): objects.update((obj, None) for obj in pack.iterobjects()) self._flush_pack_cache() # The name of the consolidated pack might match the name of a # pre-existing pack. Take care not to remove the newly created # consolidated pack. consolidated = self.add_objects(objects) old_packs.pop(consolidated.name(), None) for obj in loose_objects: self._remove_loose_object(obj.id) for name, pack in old_packs.items(): self._remove_pack(pack) self._update_pack_cache() return len(objects) def __iter__(self): """Iterate over the SHAs that are present in this store.""" iterables = (list(self.packs) + [self._iter_loose_objects()] + [self._iter_alternate_objects()]) return chain(*iterables) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose. This does not check alternates. """ return self._get_loose_object(sha) is not None def get_raw(self, name): """Obtain the raw fulltext for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ if len(name) == 40: sha = hex_to_sha(name) hexsha = name elif len(name) == 20: sha = name hexsha = None else: raise AssertionError("Invalid object name %r" % name) for pack in self.packs: try: return pack.get_raw(sha) except KeyError: pass if hexsha is None: hexsha = sha_to_hex(name) ret = self._get_loose_object(hexsha) if ret is not None: return ret.type_num, ret.as_raw_string() for alternate in self.alternates: try: return alternate.get_raw(hexsha) except KeyError: pass raise KeyError(hexsha) def add_objects(self, objects, progress=None): """Add a set of objects to this object store. :param objects: Iterable over (object, path) tuples, should support __len__. :return: Pack object of the objects written. """ return self.add_pack_data( *pack_objects_to_data(objects), progress=progress) class DiskObjectStore(PackBasedObjectStore): """Git-style object store that exists on disk.""" def __init__(self, path): """Open an object store. :param path: Path of the object store. """ super(DiskObjectStore, self).__init__() self.path = path self.pack_dir = os.path.join(self.path, PACKDIR) self._pack_cache_time = 0 self._pack_cache = {} self._alternates = None def __repr__(self): return "<%s(%r)>" % (self.__class__.__name__, self.path) @property def alternates(self): if self._alternates is not None: return self._alternates self._alternates = [] for path in self._read_alternate_paths(): self._alternates.append(DiskObjectStore(path)) return self._alternates def _read_alternate_paths(self): try: f = GitFile(os.path.join(self.path, INFODIR, "alternates"), 'rb') except (OSError, IOError) as e: if e.errno == errno.ENOENT: return raise with f: for line in f.readlines(): line = line.rstrip(b"\n") if line[0] == b"#": continue if os.path.isabs(line): yield line.decode(sys.getfilesystemencoding()) else: yield os.path.join(self.path, line).decode( sys.getfilesystemencoding()) def add_alternate_path(self, path): """Add an alternate path to this object store. """ try: os.mkdir(os.path.join(self.path, INFODIR)) except OSError as e: if e.errno != errno.EEXIST: raise alternates_path = os.path.join(self.path, INFODIR, "alternates") with GitFile(alternates_path, 'wb') as f: try: orig_f = open(alternates_path, 'rb') except (OSError, IOError) as e: if e.errno != errno.ENOENT: raise else: with orig_f: f.write(orig_f.read()) f.write(path.encode(sys.getfilesystemencoding()) + b"\n") if not os.path.isabs(path): path = os.path.join(self.path, path) self.alternates.append(DiskObjectStore(path)) def _update_pack_cache(self): try: pack_dir_contents = os.listdir(self.pack_dir) except OSError as e: if e.errno == errno.ENOENT: self._pack_cache_time = 0 self.close() return raise self._pack_cache_time = max( os.stat(self.pack_dir).st_mtime, time.time()) pack_files = set() for name in pack_dir_contents: if name.startswith("pack-") and name.endswith(".pack"): # verify that idx exists first (otherwise the pack was not yet # fully written) idx_name = os.path.splitext(name)[0] + ".idx" if idx_name in pack_dir_contents: pack_name = name[:-len(".pack")] pack_files.add(pack_name) # Open newly appeared pack files for f in pack_files: if f not in self._pack_cache: self._pack_cache[f] = Pack(os.path.join(self.pack_dir, f)) # Remove disappeared pack files for f in set(self._pack_cache) - pack_files: self._pack_cache.pop(f).close() def _pack_cache_stale(self): try: return os.stat(self.pack_dir).st_mtime >= self._pack_cache_time except OSError as e: if e.errno == errno.ENOENT: return True raise def _get_shafile_path(self, sha): # Check from object dir return hex_to_filename(self.path, sha) def _iter_loose_objects(self): for base in os.listdir(self.path): if len(base) != 2: continue for rest in os.listdir(os.path.join(self.path, base)): yield (base+rest).encode(sys.getfilesystemencoding()) def _get_loose_object(self, sha): path = self._get_shafile_path(sha) try: return ShaFile.from_path(path) except (OSError, IOError) as e: if e.errno == errno.ENOENT: return None raise def _remove_loose_object(self, sha): os.remove(self._get_shafile_path(sha)) def _remove_pack(self, pack): os.remove(pack.data.path) os.remove(pack.index.path) def _get_pack_basepath(self, entries): suffix = iter_sha1(entry[0] for entry in entries) # TODO: Handle self.pack_dir being bytes suffix = suffix.decode('ascii') return os.path.join(self.pack_dir, "pack-" + suffix) def _complete_thin_pack(self, f, path, copier, indexer): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param f: Open file object for the pack. :param path: Path to the pack file. :param copier: A PackStreamCopier to use for writing pack data. :param indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Must flush before reading (http://bugs.python.org/issue3207) f.flush() # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Must reposition before writing (http://bugs.python.org/issue3207) f.seek(0, os.SEEK_CUR) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) offset = f.tell() crc32 = write_pack_object(f, type_num, data, sha=new_sha) entries.append((ext_sha, offset, crc32)) pack_sha = new_sha.digest() f.write(pack_sha) f.close() # Move the pack in. entries.sort() pack_base_name = self._get_pack_basepath(entries) target_pack = pack_base_name + '.pack' if sys.platform == 'win32': # Windows might have the target pack file lingering. Attempt # removal, silently passing if the target does not exist. try: os.remove(target_pack) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise os.rename(path, target_pack) # Write the index. index_file = GitFile(pack_base_name + '.idx', 'wb') try: write_pack_index_v2(index_file, entries, pack_sha) index_file.close() finally: index_file.abort() # Add the pack to the store and return it. final_pack = Pack(pack_base_name) final_pack.check_length_and_checksum() self._add_known_pack(pack_base_name, final_pack) return final_pack def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. They should never be placed in the object store directly, and always indexed and completed as they are copied. :param read_all: Read function that blocks until the number of requested bytes are read. :param read_some: Read function that returns at least one byte, but may not return the number of bytes requested. :return: A Pack object pointing at the now-completed thin pack in the objects/pack directory. """ fd, path = tempfile.mkstemp(dir=self.path, prefix='tmp_pack_') with os.fdopen(fd, 'w+b') as f: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() return self._complete_thin_pack(f, path, copier, indexer) def move_in_pack(self, path): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param path: Path to the pack file. """ with PackData(path) as p: entries = p.sorted_entries() basename = self._get_pack_basepath(entries) with GitFile(basename+".idx", "wb") as f: write_pack_index_v2(f, entries, p.get_stored_checksum()) if self._pack_cache is None or self._pack_cache_stale(): self._update_pack_cache() try: return self._pack_cache[basename] except KeyError: pass target_pack = basename + '.pack' if sys.platform == 'win32': # Windows might have the target pack file lingering. Attempt # removal, silently passing if the target does not exist. try: os.remove(target_pack) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise os.rename(path, target_pack) final_pack = Pack(basename) self._add_known_pack(basename, final_pack) return final_pack def add_pack(self): """Add a new pack to this object store. :return: Fileobject to write to, a commit function to call when the pack is finished and an abort function. """ fd, path = tempfile.mkstemp(dir=self.pack_dir, suffix=".pack") f = os.fdopen(fd, 'wb') def commit(): f.flush() os.fsync(fd) f.close() if os.path.getsize(path) > 0: return self.move_in_pack(path) else: os.remove(path) return None def abort(): f.close() os.remove(path) return f, commit, abort def add_object(self, obj): """Add a single object to this object store. :param obj: Object to add """ path = self._get_shafile_path(obj.id) dir = os.path.dirname(path) try: os.mkdir(dir) except OSError as e: if e.errno != errno.EEXIST: raise if os.path.exists(path): return # Already there, no need to write again with GitFile(path, 'wb') as f: f.write(obj.as_legacy_object()) @classmethod def init(cls, path): try: os.mkdir(path) except OSError as e: if e.errno != errno.EEXIST: raise os.mkdir(os.path.join(path, "info")) os.mkdir(os.path.join(path, PACKDIR)) return cls(path) class MemoryObjectStore(BaseObjectStore): """Object store that keeps all objects in memory.""" def __init__(self): super(MemoryObjectStore, self).__init__() self._data = {} def _to_hexsha(self, sha): if len(sha) == 40: return sha elif len(sha) == 20: return sha_to_hex(sha) else: raise ValueError("Invalid sha %r" % (sha,)) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" return self._to_hexsha(sha) in self._data def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" return False def __iter__(self): """Iterate over the SHAs that are present in this store.""" return iter(self._data.keys()) @property def packs(self): """List with pack objects.""" return [] def get_raw(self, name): """Obtain the raw text for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ obj = self[self._to_hexsha(name)] return obj.type_num, obj.as_raw_string() def __getitem__(self, name): return self._data[self._to_hexsha(name)].copy() def __delitem__(self, name): """Delete an object from this store, for testing only.""" del self._data[self._to_hexsha(name)] def add_object(self, obj): """Add a single object to this object store. """ self._data[obj.id] = obj.copy() def add_objects(self, objects, progress=None): """Add a set of objects to this object store. :param objects: Iterable over a list of (object, path) tuples """ for obj, path in objects: self.add_object(obj) def add_pack(self): """Add a new pack to this object store. Because this object store doesn't support packs, we extract and add the individual objects. :return: Fileobject to write to and a commit function to call when the pack is finished. """ f = BytesIO() def commit(): p = PackData.from_file(BytesIO(f.getvalue()), f.tell()) f.close() for obj in PackInflater.for_pack_data(p, self.get_raw): self.add_object(obj) def abort(): pass return f, commit, abort def _complete_thin_pack(self, f, indexer): """Complete a thin pack by adding external references. :param f: Open file object for the pack. :param indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) write_pack_object(f, type_num, data, sha=new_sha) pack_sha = new_sha.digest() f.write(pack_sha) def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. Because this object store doesn't support packs, we extract and add the individual objects. :param read_all: Read function that blocks until the number of requested bytes are read. :param read_some: Read function that returns at least one byte, but may not return the number of bytes requested. """ f, commit, abort = self.add_pack() try: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() self._complete_thin_pack(f, indexer) except BaseException: abort() raise else: commit() class ObjectIterator(object): """Interface for iterating over objects.""" def iterobjects(self): raise NotImplementedError(self.iterobjects) class ObjectStoreIterator(ObjectIterator): """ObjectIterator that works on top of an ObjectStore.""" def __init__(self, store, sha_iter): """Create a new ObjectIterator. :param store: Object store to retrieve from :param sha_iter: Iterator over (sha, path) tuples """ self.store = store self.sha_iter = sha_iter self._shas = [] def __iter__(self): """Yield tuple with next object and path.""" for sha, path in self.itershas(): yield self.store[sha], path def iterobjects(self): """Iterate over just the objects.""" for o, path in self: yield o def itershas(self): """Iterate over the SHAs.""" for sha in self._shas: yield sha for sha in self.sha_iter: self._shas.append(sha) yield sha def __contains__(self, needle): """Check if an object is present. :note: This checks if the object is present in the underlying object store, not if it would be yielded by the iterator. :param needle: SHA1 of the object to check for """ return needle in self.store def __getitem__(self, key): """Find an object by SHA1. :note: This retrieves the object from the underlying object store. It will also succeed if the object would not be returned by the iterator. """ return self.store[key] def __len__(self): """Return the number of objects.""" return len(list(self.itershas())) def empty(self): iter = self.itershas() try: iter() except StopIteration: return True else: return False def __bool__(self): """Indicate whether this object has contents.""" return not self.empty() def tree_lookup_path(lookup_obj, root_sha, path): """Look up an object in a Git tree. :param lookup_obj: Callback for retrieving object by SHA1 :param root_sha: SHA1 of the root tree :param path: Path to lookup :return: A tuple of (mode, SHA) of the resulting path. """ tree = lookup_obj(root_sha) if not isinstance(tree, Tree): raise NotTreeError(root_sha) return tree.lookup_path(lookup_obj, path) def _collect_filetree_revs(obj_store, tree_sha, kset): """Collect SHA1s of files and directories for specified tree. :param obj_store: Object store to get objects by SHA from :param tree_sha: tree reference to walk :param kset: set to fill with references to files and directories """ filetree = obj_store[tree_sha] for name, mode, sha in filetree.iteritems(): if not S_ISGITLINK(mode) and sha not in kset: kset.add(sha) if stat.S_ISDIR(mode): _collect_filetree_revs(obj_store, sha, kset) def _split_commits_and_tags(obj_store, lst, ignore_unknown=False): """Split object id list into three lists with commit, tag, and other SHAs. Commits referenced by tags are included into commits list as well. Only SHA1s known in this repository will get through, and unless ignore_unknown argument is True, KeyError is thrown for SHA1 missing in the repository :param obj_store: Object store to get objects by SHA1 from :param lst: Collection of commit and tag SHAs :param ignore_unknown: True to skip SHA1 missing in the repository silently. :return: A tuple of (commits, tags, others) SHA1s """ commits = set() tags = set() others = set() for e in lst: try: o = obj_store[e] except KeyError: if not ignore_unknown: raise else: if isinstance(o, Commit): commits.add(e) elif isinstance(o, Tag): tags.add(e) tagged = o.object[1] c, t, o = _split_commits_and_tags( obj_store, [tagged], ignore_unknown=ignore_unknown) commits |= c tags |= t others |= o else: others.add(e) return (commits, tags, others) class MissingObjectFinder(object): """Find the objects missing from another object store. :param object_store: Object store containing at least all objects to be sent :param haves: SHA1s of commits not to send (already present in target) :param wants: SHA1s of commits to send :param progress: Optional function to report progress to. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. :param get_parents: Optional function for getting the parents of a commit. :param tagged: dict of pointed-to sha -> tag sha for including tags """ def __init__(self, object_store, haves, wants, progress=None, get_tagged=None, get_parents=lambda commit: commit.parents): self.object_store = object_store self._get_parents = get_parents # process Commits and Tags differently # Note, while haves may list commits/tags not available locally, # and such SHAs would get filtered out by _split_commits_and_tags, # wants shall list only known SHAs, and otherwise # _split_commits_and_tags fails with KeyError have_commits, have_tags, have_others = ( _split_commits_and_tags(object_store, haves, True)) want_commits, want_tags, want_others = ( _split_commits_and_tags(object_store, wants, False)) # all_ancestors is a set of commits that shall not be sent # (complete repository up to 'haves') all_ancestors = object_store._collect_ancestors( have_commits, get_parents=self._get_parents)[0] # all_missing - complete set of commits between haves and wants # common - commits from all_ancestors we hit into while # traversing parent hierarchy of wants missing_commits, common_commits = object_store._collect_ancestors( want_commits, all_ancestors, get_parents=self._get_parents) self.sha_done = set() # Now, fill sha_done with commits and revisions of # files and directories known to be both locally # and on target. Thus these commits and files # won't get selected for fetch for h in common_commits: self.sha_done.add(h) cmt = object_store[h] _collect_filetree_revs(object_store, cmt.tree, self.sha_done) # record tags we have as visited, too for t in have_tags: self.sha_done.add(t) missing_tags = want_tags.difference(have_tags) missing_others = want_others.difference(have_others) # in fact, what we 'want' is commits, tags, and others # we've found missing wants = missing_commits.union(missing_tags) wants = wants.union(missing_others) self.objects_to_send = set([(w, None, False) for w in wants]) if progress is None: self.progress = lambda x: None else: self.progress = progress self._tagged = get_tagged and get_tagged() or {} def add_todo(self, entries): self.objects_to_send.update([e for e in entries if not e[0] in self.sha_done]) def next(self): while True: if not self.objects_to_send: return None (sha, name, leaf) = self.objects_to_send.pop() if sha not in self.sha_done: break if not leaf: o = self.object_store[sha] if isinstance(o, Commit): self.add_todo([(o.tree, "", False)]) elif isinstance(o, Tree): self.add_todo([(s, n, not stat.S_ISDIR(m)) for n, m, s in o.iteritems() if not S_ISGITLINK(m)]) elif isinstance(o, Tag): self.add_todo([(o.object[1], None, False)]) if sha in self._tagged: self.add_todo([(self._tagged[sha], None, True)]) self.sha_done.add(sha) self.progress(("counting objects: %d\r" % len(self.sha_done)).encode('ascii')) return (sha, name) __next__ = next class ObjectStoreGraphWalker(object): """Graph walker that finds what commits are missing from an object store. :ivar heads: Revisions without descendants in the local repo :ivar get_parents: Function to retrieve parents in the local repo """ - def __init__(self, local_heads, get_parents): + def __init__(self, local_heads, get_parents, shallow=None): """Create a new instance. :param local_heads: Heads to start search with :param get_parents: Function for finding the parents of a SHA1. """ self.heads = set(local_heads) self.get_parents = get_parents self.parents = {} + if shallow is None: + shallow = set() + self.shallow = shallow def ack(self, sha): """Ack that a revision and its ancestors are present in the source.""" if len(sha) != 40: raise ValueError("unexpected sha %r received" % sha) ancestors = set([sha]) # stop if we run out of heads to remove while self.heads: for a in ancestors: if a in self.heads: self.heads.remove(a) # collect all ancestors new_ancestors = set() for a in ancestors: ps = self.parents.get(a) if ps is not None: new_ancestors.update(ps) self.parents[a] = None # no more ancestors; stop if not new_ancestors: break ancestors = new_ancestors def next(self): """Iterate over ancestors of heads in the target.""" if self.heads: ret = self.heads.pop() ps = self.get_parents(ret) self.parents[ret] = ps self.heads.update( [p for p in ps if p not in self.parents]) return ret return None __next__ = next def commit_tree_changes(object_store, tree, changes): """Commit a specified set of changes to a tree structure. This will apply a set of changes on top of an existing tree, storing new objects in object_store. changes are a list of tuples with (path, mode, object_sha). Paths can be both blobs and trees. See the mode and object sha to None deletes the path. This method works especially well if there are only a small number of changes to a big tree. For a large number of changes to a large tree, use e.g. commit_tree. :param object_store: Object store to store new objects in and retrieve old ones from. :param tree: Original tree root :param changes: changes to apply :return: New tree root object """ # TODO(jelmer): Save up the objects and add them using .add_objects # rather than with individual calls to .add_object. nested_changes = {} for (path, new_mode, new_sha) in changes: try: (dirname, subpath) = path.split(b'/', 1) except ValueError: if new_sha is None: del tree[path] else: tree[path] = (new_mode, new_sha) else: nested_changes.setdefault(dirname, []).append( (subpath, new_mode, new_sha)) for name, subchanges in nested_changes.items(): try: orig_subtree = object_store[tree[name][1]] except KeyError: orig_subtree = Tree() subtree = commit_tree_changes(object_store, orig_subtree, subchanges) if len(subtree) == 0: del tree[name] else: tree[name] = (stat.S_IFDIR, subtree.id) object_store.add_object(tree) return tree class OverlayObjectStore(BaseObjectStore): """Object store that can overlay multiple object stores.""" def __init__(self, bases, add_store=None): self.bases = bases self.add_store = add_store def add_object(self, object): if self.add_store is None: raise NotImplementedError(self.add_object) return self.add_store.add_object(object) def add_objects(self, objects, progress=None): if self.add_store is None: raise NotImplementedError(self.add_object) return self.add_store.add_objects(objects, progress) @property def packs(self): ret = [] for b in self.bases: ret.extend(b.packs) return ret def __iter__(self): done = set() for b in self.bases: for o_id in b: if o_id not in done: yield o_id done.add(o_id) def get_raw(self, sha_id): for b in self.bases: try: return b.get_raw(sha_id) except KeyError: pass else: raise KeyError(sha_id) def contains_packed(self, sha): for b in self.bases: if b.contains_packed(sha): return True else: return False def contains_loose(self, sha): for b in self.bases: if b.contains_loose(sha): return True else: return False def read_packs_file(f): """Yield the packs listed in a packs file.""" for line in f.read().splitlines(): if not line: continue (kind, name) = line.split(b" ", 1) if kind != b"P": continue yield name.decode(sys.getfilesystemencoding()) diff --git a/dulwich/repo.py b/dulwich/repo.py index cd992aeb..b964ef0b 100644 --- a/dulwich/repo.py +++ b/dulwich/repo.py @@ -1,1294 +1,1302 @@ # repo.py -- For dealing with git repositories. # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Repository access. This module contains the base class for git repositories (BaseRepo) and an implementation which uses a repository on local disk (Repo). """ from io import BytesIO import errno import os import sys import stat import time from dulwich.errors import ( NoIndexPresent, NotBlobError, NotCommitError, NotGitRepository, NotTreeError, NotTagError, CommitError, RefFormatError, HookError, ) from dulwich.file import ( GitFile, ) from dulwich.object_store import ( DiskObjectStore, MemoryObjectStore, ObjectStoreGraphWalker, ) from dulwich.objects import ( check_hexsha, Blob, Commit, ShaFile, Tag, Tree, ) from dulwich.pack import ( pack_objects_to_data, ) from dulwich.hooks import ( PreCommitShellHook, PostCommitShellHook, CommitMsgShellHook, ) from dulwich.refs import ( # noqa: F401 check_ref_format, RefsContainer, DictRefsContainer, InfoRefsContainer, DiskRefsContainer, read_packed_refs, read_packed_refs_with_peeled, write_packed_refs, SYMREF, ) import warnings CONTROLDIR = '.git' OBJECTDIR = 'objects' REFSDIR = 'refs' REFSDIR_TAGS = 'tags' REFSDIR_HEADS = 'heads' INDEX_FILENAME = "index" COMMONDIR = 'commondir' GITDIR = 'gitdir' WORKTREES = 'worktrees' BASE_DIRECTORIES = [ ["branches"], [REFSDIR], [REFSDIR, REFSDIR_TAGS], [REFSDIR, REFSDIR_HEADS], ["hooks"], ["info"] ] DEFAULT_REF = b'refs/heads/master' class InvalidUserIdentity(Exception): """User identity is not of the format 'user '""" def __init__(self, identity): self.identity = identity def check_user_identity(identity): """Verify that a user identity is formatted correctly. :param identity: User identity bytestring :raise InvalidUserIdentity: Raised when identity is invalid """ try: fst, snd = identity.split(b' <', 1) except ValueError: raise InvalidUserIdentity(identity) if b'>' not in snd: raise InvalidUserIdentity(identity) def parse_graftpoints(graftpoints): """Convert a list of graftpoints into a dict :param graftpoints: Iterator of graftpoint lines Each line is formatted as: []* Resulting dictionary is: : [*] https://git.wiki.kernel.org/index.php/GraftPoint """ grafts = {} for l in graftpoints: raw_graft = l.split(None, 1) commit = raw_graft[0] if len(raw_graft) == 2: parents = raw_graft[1].split() else: parents = [] for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') grafts[commit] = parents return grafts def serialize_graftpoints(graftpoints): """Convert a dictionary of grafts into string The graft dictionary is: : [*] Each line is formatted as: []* https://git.wiki.kernel.org/index.php/GraftPoint """ graft_lines = [] for commit, parents in graftpoints.items(): if parents: graft_lines.append(commit + b' ' + b' '.join(parents)) else: graft_lines.append(commit) return b'\n'.join(graft_lines) class BaseRepo(object): """Base class for a git repository. :ivar object_store: Dictionary-like object for accessing the objects :ivar refs: Dictionary-like object with the refs in this repository """ def __init__(self, object_store, refs): """Open a repository. This shouldn't be called directly, but rather through one of the base classes, such as MemoryRepo or Repo. :param object_store: Object store to use :param refs: Refs container to use """ self.object_store = object_store self.refs = refs self._graftpoints = {} self.hooks = {} def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. :return: True if permissions can be trusted, False otherwise. """ raise NotImplementedError(self._determine_file_mode) def _init_files(self, bare): """Initialize a default set of named files.""" from dulwich.config import ConfigFile self._put_named_file('description', b"Unnamed repository") f = BytesIO() cf = ConfigFile() cf.set("core", "repositoryformatversion", "0") if self._determine_file_mode(): cf.set("core", "filemode", True) else: cf.set("core", "filemode", False) cf.set("core", "bare", bare) cf.set("core", "logallrefupdates", True) cf.write_to_file(f) self._put_named_file('config', f.getvalue()) self._put_named_file(os.path.join('info', 'exclude'), b'') def get_named_file(self, path): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. :param path: The path to the file, relative to the control dir. :return: An open file object, or None if the file does not exist. """ raise NotImplementedError(self.get_named_file) def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. :param path: The path to the file, relative to the control dir. :param contents: A string to write to the file. """ raise NotImplementedError(self._put_named_file) def open_index(self): """Open the index for this repository. :raise NoIndexPresent: If no index is present :return: The matching `Index` """ raise NotImplementedError(self.open_index) - def fetch(self, target, determine_wants=None, progress=None): + def fetch(self, target, determine_wants=None, progress=None, depth=None): """Fetch objects into another repository. :param target: The target repository :param determine_wants: Optional function to determine what refs to fetch. :param progress: Optional progress function + :param depth: Optional shallow fetch depth :return: The local refs """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all count, pack_data = self.fetch_pack_data( - determine_wants, target.get_graph_walker(), progress) + determine_wants, target.get_graph_walker(), progress=progress, + depth=depth) target.object_store.add_pack_data(count, pack_data, progress) return self.get_refs() def fetch_pack_data(self, determine_wants, graph_walker, progress, - get_tagged=None): + get_tagged=None, depth=None): """Fetch the pack data required for a set of revisions. :param determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. :param graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. :param progress: Simple progress function that will be called with updated progress strings. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. + :param depth: Shallow fetch depth :return: count and iterator over pack data """ # TODO(jelmer): Fetch pack data directly, don't create objects first. objects = self.fetch_objects(determine_wants, graph_walker, progress, - get_tagged) + get_tagged, depth=depth) return pack_objects_to_data(objects) def fetch_objects(self, determine_wants, graph_walker, progress, - get_tagged=None): + get_tagged=None, depth=None): """Fetch the missing objects required for a set of revisions. :param determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. :param graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. :param progress: Simple progress function that will be called with updated progress strings. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. + :param depth: Shallow fetch depth :return: iterator over objects, with __len__ implemented """ + if depth not in (None, 0): + raise NotImplementedError("depth not supported yet") + wants = determine_wants(self.get_refs()) if not isinstance(wants, list): raise TypeError("determine_wants() did not return a list") shallows = getattr(graph_walker, 'shallow', frozenset()) unshallows = getattr(graph_walker, 'unshallow', frozenset()) if wants == []: # TODO(dborowitz): find a way to short-circuit that doesn't change # this interface. if shallows or unshallows: # Do not send a pack in shallow short-circuit path return None return [] # If the graph walker is set up with an implementation that can # ACK/NAK to the wire, it will write data to the client through # this call as a side-effect. haves = self.object_store.find_common_revisions(graph_walker) # Deal with shallow requests separately because the haves do # not reflect what objects are missing if shallows or unshallows: # TODO: filter the haves commits from iter_shas. the specific # commits aren't missing. haves = [] def get_parents(commit): if commit.id in shallows: return [] return self.get_parents(commit.id, commit) return self.object_store.iter_shas( self.object_store.find_missing_objects( haves, wants, progress, get_tagged, get_parents=get_parents)) def get_graph_walker(self, heads=None): """Retrieve a graph walker. A graph walker is used by a remote repository (or proxy) to find out which objects are present in this repository. :param heads: Repository heads to use (optional) :return: A graph walker object """ if heads is None: heads = self.refs.as_dict(b'refs/heads').values() - return ObjectStoreGraphWalker(heads, self.get_parents) + return ObjectStoreGraphWalker( + heads, self.get_parents, shallow=self.get_shallow()) def get_refs(self): """Get dictionary with all refs. :return: A ``dict`` mapping ref names to SHA1s """ return self.refs.as_dict() def head(self): """Return the SHA1 pointed at by HEAD.""" return self.refs[b'HEAD'] def _get_object(self, sha, cls): assert len(sha) in (20, 40) ret = self.get_object(sha) if not isinstance(ret, cls): if cls is Commit: raise NotCommitError(ret) elif cls is Blob: raise NotBlobError(ret) elif cls is Tree: raise NotTreeError(ret) elif cls is Tag: raise NotTagError(ret) else: raise Exception("Type invalid: %r != %r" % ( ret.type_name, cls.type_name)) return ret def get_object(self, sha): """Retrieve the object with the specified SHA. :param sha: SHA to retrieve :return: A ShaFile object :raise KeyError: when the object can not be found """ return self.object_store[sha] def get_parents(self, sha, commit=None): """Retrieve the parents of a specific commit. If the specific commit is a graftpoint, the graft parents will be returned instead. :param sha: SHA of the commit for which to retrieve the parents :param commit: Optional commit matching the sha :return: List of parents """ try: return self._graftpoints[sha] except KeyError: if commit is None: commit = self[sha] return commit.parents def get_config(self): """Retrieve the config object. :return: `ConfigFile` object for the ``.git/config`` file. """ raise NotImplementedError(self.get_config) def get_description(self): """Retrieve the description for this repository. :return: String with the description of the repository as set by the user. """ raise NotImplementedError(self.get_description) def set_description(self, description): """Set the description for this repository. :param description: Text to set as description for this repository. """ raise NotImplementedError(self.set_description) def get_config_stack(self): """Return a config stack for this repository. This stack accesses the configuration for both this repository itself (.git/config) and the global configuration, which usually lives in ~/.gitconfig. :return: `Config` instance for this repository """ from dulwich.config import StackedConfig backends = [self.get_config()] + StackedConfig.default_backends() return StackedConfig(backends, writable=backends[0]) def get_shallow(self): """Get the set of shallow commits. :return: Set of shallow commits. """ return set() def get_peeled(self, ref): """Get the peeled value of a ref. :param ref: The refname to peel. :return: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ cached = self.refs.get_peeled(ref) if cached is not None: return cached return self.object_store.peel_sha(self.refs[ref]).id def get_walker(self, include=None, *args, **kwargs): """Obtain a walker for this repository. :param include: Iterable of SHAs of commits to include along with their ancestors. Defaults to [HEAD] :param exclude: Iterable of SHAs of commits to exclude along with their ancestors, overriding includes. :param order: ORDER_* constant specifying the order of results. Anything other than ORDER_DATE may result in O(n) memory usage. :param reverse: If True, reverse the order of output, requiring O(n) memory. :param max_entries: The maximum number of entries to yield, or None for no limit. :param paths: Iterable of file or subtree paths to show entries for. :param rename_detector: diff.RenameDetector object for detecting renames. :param follow: If True, follow path across renames/copies. Forces a default rename_detector. :param since: Timestamp to list commits after. :param until: Timestamp to list commits before. :param queue_cls: A class to use for a queue of commits, supporting the iterator protocol. The constructor takes a single argument, the Walker. :return: A `Walker` object """ from dulwich.walk import Walker if include is None: include = [self.head()] if isinstance(include, str): include = [include] kwargs['get_parents'] = lambda commit: self.get_parents( commit.id, commit) return Walker(self.object_store, include, *args, **kwargs) def __getitem__(self, name): """Retrieve a Git object by SHA1 or ref. :param name: A Git object SHA1 or a ref name :return: A `ShaFile` object, such as a Commit or Blob :raise KeyError: when the specified ref or object does not exist """ if not isinstance(name, bytes): raise TypeError("'name' must be bytestring, not %.80s" % type(name).__name__) if len(name) in (20, 40): try: return self.object_store[name] except (KeyError, ValueError): pass try: return self.object_store[self.refs[name]] except RefFormatError: raise KeyError(name) def __contains__(self, name): """Check if a specific Git object or ref is present. :param name: Git object SHA1 or ref name """ if len(name) in (20, 40): return name in self.object_store or name in self.refs else: return name in self.refs def __setitem__(self, name, value): """Set a ref. :param name: ref name :param value: Ref value - either a ShaFile object, or a hex sha """ if name.startswith(b"refs/") or name == b'HEAD': if isinstance(value, ShaFile): self.refs[name] = value.id elif isinstance(value, bytes): self.refs[name] = value else: raise TypeError(value) else: raise ValueError(name) def __delitem__(self, name): """Remove a ref. :param name: Name of the ref to remove """ if name.startswith(b"refs/") or name == b"HEAD": del self.refs[name] else: raise ValueError(name) def _get_user_identity(self, config): """Determine the identity to use for new commits. """ user = os.environ.get("GIT_COMMITTER_NAME") email = os.environ.get("GIT_COMMITTER_EMAIL") if user is None: try: user = config.get(("user", ), "name") except KeyError: user = None if email is None: try: email = config.get(("user", ), "email") except KeyError: email = None if user is None: import getpass user = getpass.getuser().encode(sys.getdefaultencoding()) if email is None: import getpass import socket email = ("{}@{}".format(getpass.getuser(), socket.gethostname()) .encode(sys.getdefaultencoding())) return (user + b" <" + email + b">") def _add_graftpoints(self, updated_graftpoints): """Add or modify graftpoints :param updated_graftpoints: Dict of commit shas to list of parent shas """ # Simple validation for commit, parents in updated_graftpoints.items(): for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') self._graftpoints.update(updated_graftpoints) def _remove_graftpoints(self, to_remove=[]): """Remove graftpoints :param to_remove: List of commit shas """ for sha in to_remove: del self._graftpoints[sha] def do_commit(self, message=None, committer=None, author=None, commit_timestamp=None, commit_timezone=None, author_timestamp=None, author_timezone=None, tree=None, encoding=None, ref=b'HEAD', merge_heads=None): """Create a new commit. :param message: Commit message :param committer: Committer fullname :param author: Author fullname (defaults to committer) :param commit_timestamp: Commit timestamp (defaults to now) :param commit_timezone: Commit timestamp timezone (defaults to GMT) :param author_timestamp: Author timestamp (defaults to commit timestamp) :param author_timezone: Author timestamp timezone (defaults to commit timestamp timezone) :param tree: SHA1 of the tree root to use (if not specified the current index will be committed). :param encoding: Encoding :param ref: Optional ref to commit to (defaults to current branch) :param merge_heads: Merge heads (defaults to .git/MERGE_HEADS) :return: New commit SHA1 """ import time c = Commit() if tree is None: index = self.open_index() c.tree = index.commit(self.object_store) else: if len(tree) != 40: raise ValueError("tree must be a 40-byte hex sha string") c.tree = tree try: self.hooks['pre-commit'].execute() except HookError as e: raise CommitError(e) except KeyError: # no hook defined, silent fallthrough pass config = self.get_config_stack() if merge_heads is None: # FIXME: Read merge heads from .git/MERGE_HEADS merge_heads = [] if committer is None: committer = self._get_user_identity(config) check_user_identity(committer) c.committer = committer if commit_timestamp is None: # FIXME: Support GIT_COMMITTER_DATE environment variable commit_timestamp = time.time() c.commit_time = int(commit_timestamp) if commit_timezone is None: # FIXME: Use current user timezone rather than UTC commit_timezone = 0 c.commit_timezone = commit_timezone if author is None: # FIXME: Support GIT_AUTHOR_NAME/GIT_AUTHOR_EMAIL environment # variables author = committer c.author = author check_user_identity(author) if author_timestamp is None: # FIXME: Support GIT_AUTHOR_DATE environment variable author_timestamp = commit_timestamp c.author_time = int(author_timestamp) if author_timezone is None: author_timezone = commit_timezone c.author_timezone = author_timezone if encoding is None: try: encoding = config.get(('i18n', ), 'commitEncoding') except KeyError: pass # No dice if encoding is not None: c.encoding = encoding if message is None: # FIXME: Try to read commit message from .git/MERGE_MSG raise ValueError("No commit message specified") try: c.message = self.hooks['commit-msg'].execute(message) if c.message is None: c.message = message except HookError as e: raise CommitError(e) except KeyError: # no hook defined, message not modified c.message = message if ref is None: # Create a dangling commit c.parents = merge_heads self.object_store.add_object(c) else: try: old_head = self.refs[ref] c.parents = [old_head] + merge_heads self.object_store.add_object(c) ok = self.refs.set_if_equals( ref, old_head, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) except KeyError: c.parents = merge_heads self.object_store.add_object(c) ok = self.refs.add_if_new( ref, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) if not ok: # Fail if the atomic compare-and-swap failed, leaving the # commit and all its objects as garbage. raise CommitError("%s changed during commit" % (ref,)) try: self.hooks['post-commit'].execute() except HookError as e: # silent failure warnings.warn("post-commit hook failed: %s" % e, UserWarning) except KeyError: # no hook defined, silent fallthrough pass return c.id def read_gitfile(f): """Read a ``.git`` file. The first line of the file should start with "gitdir: " :param f: File-like object to read from :return: A path """ cs = f.read() if not cs.startswith("gitdir: "): raise ValueError("Expected file to start with 'gitdir: '") return cs[len("gitdir: "):].rstrip("\n") class Repo(BaseRepo): """A git repository backed by local disk. To open an existing repository, call the contructor with the path of the repository. To create a new repository, use the Repo.init class method. """ def __init__(self, root): hidden_path = os.path.join(root, CONTROLDIR) if os.path.isdir(os.path.join(hidden_path, OBJECTDIR)): self.bare = False self._controldir = hidden_path elif (os.path.isdir(os.path.join(root, OBJECTDIR)) and os.path.isdir(os.path.join(root, REFSDIR))): self.bare = True self._controldir = root elif os.path.isfile(hidden_path): self.bare = False with open(hidden_path, 'r') as f: path = read_gitfile(f) self.bare = False self._controldir = os.path.join(root, path) else: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=root) ) commondir = self.get_named_file(COMMONDIR) if commondir is not None: with commondir: self._commondir = os.path.join( self.controldir(), commondir.read().rstrip(b"\r\n").decode( sys.getfilesystemencoding())) else: self._commondir = self._controldir self.path = root object_store = DiskObjectStore( os.path.join(self.commondir(), OBJECTDIR)) refs = DiskRefsContainer(self.commondir(), self._controldir, logger=self._write_reflog) BaseRepo.__init__(self, object_store, refs) self._graftpoints = {} graft_file = self.get_named_file(os.path.join("info", "grafts"), basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) graft_file = self.get_named_file("shallow", basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) self.hooks['pre-commit'] = PreCommitShellHook(self.controldir()) self.hooks['commit-msg'] = CommitMsgShellHook(self.controldir()) self.hooks['post-commit'] = PostCommitShellHook(self.controldir()) def _write_reflog(self, ref, old_sha, new_sha, committer, timestamp, timezone, message): from .reflog import format_reflog_line path = os.path.join( self.controldir(), 'logs', ref.decode(sys.getfilesystemencoding())) try: os.makedirs(os.path.dirname(path)) except OSError as e: if e.errno != errno.EEXIST: raise if committer is None: config = self.get_config_stack() committer = self._get_user_identity(config) check_user_identity(committer) if timestamp is None: timestamp = int(time.time()) if timezone is None: timezone = 0 # FIXME with open(path, 'ab') as f: f.write(format_reflog_line(old_sha, new_sha, committer, timestamp, timezone, message) + b'\n') @classmethod def discover(cls, start='.'): """Iterate parent directories to discover a repository Return a Repo object for the first parent directory that looks like a Git repository. :param start: The directory to start discovery from (defaults to '.') """ remaining = True path = os.path.abspath(start) while remaining: try: return cls(path) except NotGitRepository: path, remaining = os.path.split(path) raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=start) ) def controldir(self): """Return the path of the control directory.""" return self._controldir def commondir(self): """Return the path of the common directory. For a main working tree, it is identical to controldir(). For a linked working tree, it is the control directory of the main working tree.""" return self._commondir def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. :return: True if permissions can be trusted, False otherwise. """ fname = os.path.join(self.path, '.probe-permissions') with open(fname, 'w') as f: f.write('') st1 = os.lstat(fname) os.chmod(fname, st1.st_mode ^ stat.S_IXUSR) st2 = os.lstat(fname) os.unlink(fname) mode_differs = st1.st_mode != st2.st_mode st2_has_exec = (st2.st_mode & stat.S_IXUSR) != 0 return mode_differs and st2_has_exec def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. :param path: The path to the file, relative to the control dir. :param contents: A string to write to the file. """ path = path.lstrip(os.path.sep) with GitFile(os.path.join(self.controldir(), path), 'wb') as f: f.write(contents) def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. :param path: The path to the file, relative to the control dir. :param basedir: Optional argument that specifies an alternative to the control dir. :return: An open file object, or None if the file does not exist. """ # TODO(dborowitz): sanitize filenames, since this is used directly by # the dumb web serving code. if basedir is None: basedir = self.controldir() path = path.lstrip(os.path.sep) try: return open(os.path.join(basedir, path), 'rb') except (IOError, OSError) as e: if e.errno == errno.ENOENT: return None raise def get_shallow(self): f = self.get_named_file('shallow') if f is None: return set() with f: return set(l.strip() for l in f) def index_path(self): """Return path to the index file.""" return os.path.join(self.controldir(), INDEX_FILENAME) def open_index(self): """Open the index for this repository. :raise NoIndexPresent: If no index is present :return: The matching `Index` """ from dulwich.index import Index if not self.has_index(): raise NoIndexPresent() return Index(self.index_path()) def has_index(self): """Check if an index is present.""" # Bare repos must never have index files; non-bare repos may have a # missing index file, which is treated as empty. return not self.bare def stage(self, fs_paths): """Stage a set of paths. :param fs_paths: List of paths, relative to the repository path """ root_path_bytes = self.path.encode(sys.getfilesystemencoding()) if not isinstance(fs_paths, list): fs_paths = [fs_paths] from dulwich.index import ( blob_from_path_and_stat, index_entry_from_stat, _fs_to_tree_path, ) index = self.open_index() for fs_path in fs_paths: if not isinstance(fs_path, bytes): fs_path = fs_path.encode(sys.getfilesystemencoding()) if os.path.isabs(fs_path): raise ValueError( "path %r should be relative to " "repository root, not absolute" % fs_path) tree_path = _fs_to_tree_path(fs_path) full_path = os.path.join(root_path_bytes, fs_path) try: st = os.lstat(full_path) except OSError: # File no longer exists try: del index[tree_path] except KeyError: pass # already removed else: if not stat.S_ISDIR(st.st_mode): blob = blob_from_path_and_stat(full_path, st) self.object_store.add_object(blob) index[tree_path] = index_entry_from_stat(st, blob.id, 0) else: try: del index[tree_path] except KeyError: pass index.write() def clone(self, target_path, mkdir=True, bare=False, origin=b"origin", checkout=None): """Clone this repository. :param target_path: Target path :param mkdir: Create the target directory :param bare: Whether to create a bare repository :param origin: Base name for refs in target repository cloned from this repository :return: Created repository as `Repo` """ if not bare: target = self.init(target_path, mkdir=mkdir) else: if checkout: raise ValueError("checkout and bare are incompatible") target = self.init_bare(target_path, mkdir=mkdir) self.fetch(target) encoded_path = self.path if not isinstance(encoded_path, bytes): encoded_path = encoded_path.encode(sys.getfilesystemencoding()) ref_message = b"clone: from " + encoded_path target.refs.import_refs( b'refs/remotes/' + origin, self.refs.as_dict(b'refs/heads'), message=ref_message) target.refs.import_refs( b'refs/tags', self.refs.as_dict(b'refs/tags'), message=ref_message) try: target.refs.add_if_new( DEFAULT_REF, self.refs[DEFAULT_REF], message=ref_message) except KeyError: pass target_config = target.get_config() target_config.set(('remote', 'origin'), 'url', encoded_path) target_config.set(('remote', 'origin'), 'fetch', '+refs/heads/*:refs/remotes/origin/*') target_config.write_to_path() # Update target head head_chain, head_sha = self.refs.follow(b'HEAD') if head_chain and head_sha is not None: target.refs.set_symbolic_ref(b'HEAD', head_chain[-1], message=ref_message) target[b'HEAD'] = head_sha if checkout is None: checkout = (not bare) if checkout: # Checkout HEAD to target dir target.reset_index() return target def reset_index(self, tree=None): """Reset the index back to a specific tree. :param tree: Tree SHA to reset to, None for current HEAD tree. """ from dulwich.index import ( build_index_from_tree, validate_path_element_default, validate_path_element_ntfs, ) if tree is None: tree = self[b'HEAD'].tree config = self.get_config() honor_filemode = config.get_boolean( b'core', b'filemode', os.name != "nt") if config.get_boolean(b'core', b'core.protectNTFS', os.name == "nt"): validate_path_element = validate_path_element_ntfs else: validate_path_element = validate_path_element_default return build_index_from_tree( self.path, self.index_path(), self.object_store, tree, honor_filemode=honor_filemode, validate_path_element=validate_path_element) def get_config(self): """Retrieve the config object. :return: `ConfigFile` object for the ``.git/config`` file. """ from dulwich.config import ConfigFile path = os.path.join(self._controldir, 'config') try: return ConfigFile.from_path(path) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise ret = ConfigFile() ret.path = path return ret def get_description(self): """Retrieve the description of this repository. :return: A string describing the repository or None. """ path = os.path.join(self._controldir, 'description') try: with GitFile(path, 'rb') as f: return f.read() except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise return None def __repr__(self): return "" % self.path def set_description(self, description): """Set the description for this repository. :param description: Text to set as description for this repository. """ self._put_named_file('description', description) @classmethod def _init_maybe_bare(cls, path, bare): for d in BASE_DIRECTORIES: os.mkdir(os.path.join(path, *d)) DiskObjectStore.init(os.path.join(path, OBJECTDIR)) ret = cls(path) ret.refs.set_symbolic_ref(b'HEAD', DEFAULT_REF) ret._init_files(bare) return ret @classmethod def init(cls, path, mkdir=False): """Create a new repository. :param path: Path in which to create the repository :param mkdir: Whether to create the directory :return: `Repo` instance """ if mkdir: os.mkdir(path) controldir = os.path.join(path, CONTROLDIR) os.mkdir(controldir) cls._init_maybe_bare(controldir, False) return cls(path) @classmethod def _init_new_working_directory(cls, path, main_repo, identifier=None, mkdir=False): """Create a new working directory linked to a repository. :param path: Path in which to create the working tree. :param main_repo: Main repository to reference :param identifier: Worktree identifier :param mkdir: Whether to create the directory :return: `Repo` instance """ if mkdir: os.mkdir(path) if identifier is None: identifier = os.path.basename(path) main_worktreesdir = os.path.join(main_repo.controldir(), WORKTREES) worktree_controldir = os.path.join(main_worktreesdir, identifier) gitdirfile = os.path.join(path, CONTROLDIR) with open(gitdirfile, 'wb') as f: f.write(b'gitdir: ' + worktree_controldir.encode(sys.getfilesystemencoding()) + b'\n') try: os.mkdir(main_worktreesdir) except OSError as e: if e.errno != errno.EEXIST: raise try: os.mkdir(worktree_controldir) except OSError as e: if e.errno != errno.EEXIST: raise with open(os.path.join(worktree_controldir, GITDIR), 'wb') as f: f.write(gitdirfile.encode(sys.getfilesystemencoding()) + b'\n') with open(os.path.join(worktree_controldir, COMMONDIR), 'wb') as f: f.write(b'../..\n') with open(os.path.join(worktree_controldir, 'HEAD'), 'wb') as f: f.write(main_repo.head() + b'\n') r = cls(path) r.reset_index() return r @classmethod def init_bare(cls, path, mkdir=False): """Create a new bare repository. ``path`` should already exist and be an empty directory. :param path: Path to create bare repository in :return: a `Repo` instance """ if mkdir: os.mkdir(path) return cls._init_maybe_bare(path, True) create = init_bare def close(self): """Close any files opened by this repository.""" self.object_store.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() class MemoryRepo(BaseRepo): """Repo that stores refs, objects, and named files in memory. MemoryRepos are always bare: they have no working tree and no index, since those have a stronger dependency on the filesystem. """ def __init__(self): from dulwich.config import ConfigFile self._reflog = [] refs_container = DictRefsContainer({}, logger=self._append_reflog) BaseRepo.__init__(self, MemoryObjectStore(), refs_container) self._named_files = {} self.bare = True self._config = ConfigFile() self._description = None def _append_reflog(self, *args): self._reflog.append(args) def set_description(self, description): self._description = description def get_description(self): return self._description def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. :return: True if permissions can be trusted, False otherwise. """ return sys.platform != 'win32' def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. :param path: The path to the file, relative to the control dir. :param contents: A string to write to the file. """ self._named_files[path] = contents def get_named_file(self, path): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-baked Repo, the object returned need not be pointing to a file in that location. :param path: The path to the file, relative to the control dir. :return: An open file object, or None if the file does not exist. """ contents = self._named_files.get(path, None) if contents is None: return None return BytesIO(contents) def open_index(self): """Fail to open index for this repo, since it is bare. :raise NoIndexPresent: Raised when no index is present """ raise NoIndexPresent() def get_config(self): """Retrieve the config object. :return: `ConfigFile` object. """ return self._config @classmethod def init_bare(cls, objects, refs): """Create a new bare repository in memory. :param objects: Objects for the new repository, as iterable :param refs: Refs as dictionary, mapping names to object SHA1s """ ret = cls() for obj in objects: ret.object_store.add_object(obj) for refname, sha in refs.items(): ret.refs.add_if_new(refname, sha) ret._init_files(bare=True) return ret diff --git a/dulwich/tests/test_client.py b/dulwich/tests/test_client.py index e5b70778..e9fa573b 100644 --- a/dulwich/tests/test_client.py +++ b/dulwich/tests/test_client.py @@ -1,1218 +1,1218 @@ # test_client.py -- Tests for the git protocol, client side # Copyright (C) 2009 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # from io import BytesIO import base64 import sys import shutil import tempfile import warnings try: from urllib import quote as urlquote except ImportError: from urllib.parse import quote as urlquote try: import urlparse except ImportError: import urllib.parse as urlparse import urllib3 import dulwich from dulwich import ( client, ) from dulwich.client import ( InvalidWants, LocalGitClient, TraditionalGitClient, TCPGitClient, SSHGitClient, HttpGitClient, ReportStatusParser, SendPackError, StrangeHostname, SubprocessSSHVendor, PLinkSSHVendor, UpdateRefsError, check_wants, default_urllib3_manager, get_transport_and_path, get_transport_and_path_from_url, parse_rsync_url, ) from dulwich.config import ( ConfigDict, ) from dulwich.tests import ( TestCase, ) from dulwich.protocol import ( TCP_GIT_PORT, Protocol, ) from dulwich.pack import ( pack_objects_to_data, write_pack_data, write_pack_objects, ) from dulwich.objects import ( Commit, Tree ) from dulwich.repo import ( MemoryRepo, Repo, ) from dulwich.tests import skipIf from dulwich.tests.utils import ( open_repo, tear_down_repo, setup_warning_catcher, ) class DummyClient(TraditionalGitClient): def __init__(self, can_read, read, write): self.can_read = can_read self.read = read self.write = write TraditionalGitClient.__init__(self) def _connect(self, service, path): return Protocol(self.read, self.write), self.can_read, None class DummyPopen(): def __init__(self, *args, **kwards): self.stdin = BytesIO(b"stdin") self.stdout = BytesIO(b"stdout") self.stderr = BytesIO(b"stderr") self.returncode = 0 self.args = args self.kwargs = kwards def communicate(self, *args, **kwards): return ('Running', '') def wait(self, *args, **kwards): return False # TODO(durin42): add unit-level tests of GitClient class GitClientTests(TestCase): def setUp(self): super(GitClientTests, self).setUp() self.rout = BytesIO() self.rin = BytesIO() self.client = DummyClient(lambda x: True, self.rin.read, self.rout.write) def test_caps(self): agent_cap = ( 'agent=dulwich/%d.%d.%d' % dulwich.__version__).encode('ascii') self.assertEqual(set([b'multi_ack', b'side-band-64k', b'ofs-delta', - b'thin-pack', b'multi_ack_detailed', + b'thin-pack', b'multi_ack_detailed', b'shallow', agent_cap]), set(self.client._fetch_capabilities)) self.assertEqual(set([b'ofs-delta', b'report-status', b'side-band-64k', agent_cap]), set(self.client._send_capabilities)) def test_archive_ack(self): self.rin.write( b'0009NACK\n' b'0000') self.rin.seek(0) self.client.archive(b'bla', b'HEAD', None, None) self.assertEqual(self.rout.getvalue(), b'0011argument HEAD0000') def test_fetch_empty(self): self.rin.write(b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual(heads, {}) return [] ret = self.client.fetch_pack(b'/', check_heads, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) def test_fetch_pack_ignores_magic_ref(self): self.rin.write( b'00000000000000000000000000000000000000000000 capabilities^{}' b'\x00 multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual({}, heads) return [] ret = self.client.fetch_pack(b'bla', check_heads, None, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') def test_fetch_pack_none(self): self.rin.write( b'008855dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 HEAD\x00multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) ret = self.client.fetch_pack( b'bla', lambda heads: [], None, None, None) self.assertEqual( {b'HEAD': b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7'}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') def test_fetch_pack_sha_not_in_ref(self): self.rin.write( b'008855dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 HEAD\x00multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) self.assertRaises( InvalidWants, self.client.fetch_pack, b'bla', lambda heads: ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'], None, None, None) def test_send_pack_no_sideband64k_with_update_ref_error(self): # No side-bank-64k reported by server shouldn't try to parse # side band data pkts = [b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 capabilities^{}' b'\x00 report-status delete-refs ofs-delta\n', b'', b"unpack ok", b"ng refs/foo/bar pre-receive hook declined", b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' def update_refs(refs): return {b'refs/foo/bar': commit.id, } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, ''), ]) self.assertRaises(UpdateRefsError, self.client.send_pack, "blah", update_refs, generate_pack_data) def test_send_pack_none(self): self.rin.write( b'0078310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ' b'side-band-64k quiet ofs-delta\n' b'0000') self.rin.seek(0) def update_refs(refs): return { b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual(self.rout.getvalue(), b'0000') def test_send_pack_keep_and_delete(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'003f310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/keepme\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00report-status ofs-delta0000', b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00ofs-delta report-status0000']) def test_send_pack_delete_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00report-status ofs-delta0000', b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00ofs-delta report-status0000']) def test_send_pack_new_ref_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) def update_refs(refs): return { b'refs/heads/blah12': b'310ca9477129b8586fa2afc779c1f57cf64bba6c', b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] f = BytesIO() write_pack_objects(f, {}) self.client.send_pack('/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f0000000000000000000000000000000000000000 ' b'310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/blah12\x00report-status ofs-delta0000' + f.getvalue(), b'007f0000000000000000000000000000000000000000 ' b'310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/blah12\x00ofs-delta report-status0000' + f.getvalue()]) def test_send_pack_new_ref(self): self.rin.write( b'0064310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' def update_refs(refs): return { b'refs/heads/blah12': commit.id, b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, b''), ]) f = BytesIO() write_pack_data(f, *generate_pack_data(None, None)) self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f0000000000000000000000000000000000000000 ' + commit.id + b' refs/heads/blah12\x00report-status ofs-delta0000' + f.getvalue(), b'007f0000000000000000000000000000000000000000 ' + commit.id + b' refs/heads/blah12\x00ofs-delta report-status0000' + f.getvalue()]) def test_send_pack_no_deleteref_delete_only(self): pkts = [b'310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/master' b'\x00 report-status ofs-delta\n', b'', b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.assertRaises(UpdateRefsError, self.client.send_pack, b"/", update_refs, generate_pack_data) self.assertEqual(self.rout.getvalue(), b'0000') class TestGetTransportAndPath(TestCase): def test_tcp(self): c, path = get_transport_and_path('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_git_ssh_explicit(self): c, path = get_transport_and_path('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path('ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_username_and_port_explicit_unknown_scheme(self): c, path = get_transport_and_path( 'unknown://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('unknown', c.host) self.assertEqual('//git@server:7999/dply/stuff.git', path) def test_username_and_port_explicit(self): c, path = get_transport_and_path( 'ssh://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('git', c.username) self.assertEqual('server', c.host) self.assertEqual(7999, c.port) self.assertEqual('/dply/stuff.git', path) def test_ssh_abspath_doubleslash(self): c, path = get_transport_and_path('git+ssh://foo.com//bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('//bar/baz', path) def test_ssh_port(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_implicit(self): c, path = get_transport_and_path('foo:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_host(self): c, path = get_transport_and_path('foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_user_host(self): c, path = get_transport_and_path('user@foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('/bar/baz', path) def test_ssh_relpath(self): c, path = get_transport_and_path('foo:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_host_relpath(self): c, path = get_transport_and_path('foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_user_host_relpath(self): c, path = get_transport_and_path('user@foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('bar/baz', path) def test_local(self): c, path = get_transport_and_path('foo.bar/baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('foo.bar/baz', path) @skipIf(sys.platform != 'win32', 'Behaviour only happens on windows.') def test_local_abs_windows_path(self): c, path = get_transport_and_path('C:\\foo.bar\\baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('C:\\foo.bar\\baz', path) def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 c, path = get_transport_and_path('prospero://bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_http_auth(self): url = 'https://user:passwd@github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) def test_http_auth_with_username(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path( url, username='user2', password='blah') self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user2', c._username) self.assertEqual('blah', c._password) def test_http_auth_with_username_and_in_url(self): url = 'https://user:passwd@github.com/jelmer/dulwich' c, path = get_transport_and_path( url, username='user2', password='blah') self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) def test_http_no_auth(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertIs(None, c._username) self.assertIs(None, c._password) class TestGetTransportAndPathFromUrl(TestCase): def test_tcp(self): c, path = get_transport_and_path_from_url('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path_from_url('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path_from_url('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/~/bar/baz', path) def test_ssh_port_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/~/bar/baz', path) def test_ssh_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.com:bar/baz') def test_ssh_user_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'user@foo.com:bar/baz') def test_local_path(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.bar/baz') def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 self.assertRaises( ValueError, get_transport_and_path_from_url, 'prospero://bar/baz') def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path_from_url(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_file(self): c, path = get_transport_and_path_from_url('file:///home/jelmer/foo') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('/home/jelmer/foo', path) class TestSSHVendor(object): def __init__(self): self.host = None self.command = "" self.username = None self.port = None self.password = None self.key_filename = None def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): self.host = host self.command = command self.username = username self.port = port self.password = password self.key_filename = key_filename class Subprocess: pass setattr(Subprocess, 'read', lambda: None) setattr(Subprocess, 'write', lambda: None) setattr(Subprocess, 'close', lambda: None) setattr(Subprocess, 'can_read', lambda: None) return Subprocess() class SSHGitClientTests(TestCase): def setUp(self): super(SSHGitClientTests, self).setUp() self.server = TestSSHVendor() self.real_vendor = client.get_ssh_vendor client.get_ssh_vendor = lambda: self.server self.client = SSHGitClient('git.samba.org') def tearDown(self): super(SSHGitClientTests, self).tearDown() client.get_ssh_vendor = self.real_vendor def test_get_url(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org') url = c.get_url(path) self.assertEqual('ssh://git.samba.org/tmp/repo.git', url) def test_get_url_with_username_and_port(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org', port=2222, username='user') url = c.get_url(path) self.assertEqual('ssh://user@git.samba.org:2222/tmp/repo.git', url) def test_default_command(self): self.assertEqual( b'git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack') self.assertEqual( b'/usr/lib/git/git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path_spaces(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack -ibla') self.assertEqual(b"/usr/lib/git/git-upload-pack -ibla", self.client._get_cmd_path(b'upload-pack')) def test_connect(self): server = self.server client = self.client client.username = b"username" client.port = 1337 client._connect(b"command", b"/path/to/repo") self.assertEqual(b"username", server.username) self.assertEqual(1337, server.port) self.assertEqual("git-command '/path/to/repo'", server.command) client._connect(b"relative-command", b"/~/path/to/repo") self.assertEqual("git-relative-command '~/path/to/repo'", server.command) class ReportStatusParserTests(TestCase): def test_invalid_pack(self): parser = ReportStatusParser() parser.handle_packet(b"unpack error - foo bar") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) self.assertRaises(SendPackError, parser.check) def test_update_refs_error(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ng refs/foo/bar need to pull") parser.handle_packet(None) self.assertRaises(UpdateRefsError, parser.check) def test_ok(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) parser.check() class LocalGitClientTests(TestCase): def test_get_url(self): path = "/tmp/repo.git" c = LocalGitClient() url = c.get_url(path) self.assertEqual('file:///tmp/repo.git', url) def test_fetch_into_empty(self): c = LocalGitClient() t = MemoryRepo() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) self.assertEqual(s.get_refs(), c.fetch(s.path, t).refs) def test_fetch_empty(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = {} ret = c.fetch_pack( s.path, lambda heads: [], graph_walker=walker, pack_data=out.write) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) self.assertEqual( {b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual( b"PACK\x00\x00\x00\x02\x00\x00\x00\x00\x02\x9d\x08" b"\x82;\xd8\xa8\xea\xb5\x10\xadj\xc7\\\x82<\xfd>\xd3\x1e", out.getvalue()) def test_fetch_pack_none(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = MemoryRepo().get_graph_walker() ret = c.fetch_pack( s.path, lambda heads: [b"a90fa2d900a17e99b433217e988c4eb4a2e9a097"], graph_walker=walker, pack_data=out.write) self.assertEqual({b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) # Hardcoding is not ideal, but we'll fix that some other day.. self.assertTrue(out.getvalue().startswith( b'PACK\x00\x00\x00\x02\x00\x00\x00\x07')) def test_send_pack_without_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target = open_repo('a.git') self.addCleanup(tear_down_repo, target) self.send_and_verify(b"master", local, target) def test_send_pack_with_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) with Repo.init_bare(target_path) as target: self.send_and_verify(b"master", local, target) def test_get_refs(self): local = open_repo('refs.git') self.addCleanup(tear_down_repo, local) client = LocalGitClient() refs = client.get_refs(local.path) self.assertDictEqual(local.refs.as_dict(), refs) def send_and_verify(self, branch, local, target): """Send branch from local to remote repository and verify it worked.""" client = LocalGitClient() ref_name = b"refs/heads/" + branch new_refs = client.send_pack(target.path, lambda _: {ref_name: local.refs[ref_name]}, local.object_store.generate_pack_data) self.assertEqual(local.refs[ref_name], new_refs[ref_name]) obj_local = local.get_object(new_refs[ref_name]) obj_target = target.get_object(new_refs[ref_name]) self.assertEqual(obj_local, obj_target) class HttpGitClientTests(TestCase): @staticmethod def b64encode(s): """Python 2/3 compatible Base64 encoder. Returns string.""" try: return base64.b64encode(s) except TypeError: return base64.b64encode(s.encode('latin1')).decode('ascii') def test_get_url(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_bytes_path(self): base_url = 'https://github.com/jelmer/dulwich' path_bytes = b'/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path_bytes) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_with_username_and_passwd(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url, username='USERNAME', password='PASSWD') url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_init_username_passwd_set(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None, username='user', password='passwd') self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % ('user', 'passwd') b64_credentials = self.b64encode(auth_string) expected_basic_auth = 'Basic %s' % b64_credentials self.assertEqual(basic_auth, expected_basic_auth) def test_init_no_username_passwd(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None) self.assertIs(None, c._username) self.assertIs(None, c._password) self.assertNotIn('authorization', c.pool_manager.headers) def test_from_parsedurl_on_url_with_quoted_credentials(self): original_username = 'john|the|first' quoted_username = urlquote(original_username) original_password = 'Ya#1$2%3' quoted_password = urlquote(original_password) url = 'https://{username}:{password}@github.com/jelmer/dulwich'.format( username=quoted_username, password=quoted_password ) c = HttpGitClient.from_parsedurl(urlparse.urlparse(url)) self.assertEqual(original_username, c._username) self.assertEqual(original_password, c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % (original_username, original_password) b64_credentials = self.b64encode(auth_string) expected_basic_auth = 'Basic %s' % str(b64_credentials) self.assertEqual(basic_auth, expected_basic_auth) class TCPGitClientTests(TestCase): def test_get_url(self): host = 'github.com' path = '/jelmer/dulwich' c = TCPGitClient(host) url = c.get_url(path) self.assertEqual('git://github.com/jelmer/dulwich', url) def test_get_url_with_port(self): host = 'github.com' path = '/jelmer/dulwich' port = 9090 c = TCPGitClient(host, port=port) url = c.get_url(path) self.assertEqual('git://github.com:9090/jelmer/dulwich', url) class DefaultUrllib3ManagerTest(TestCase): def test_no_config(self): manager = default_urllib3_manager(config=None) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_proxy(self): manager = default_urllib3_manager(config=ConfigDict()) self.assertNotIsInstance(manager, urllib3.ProxyManager) def test_config_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'true') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'false') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') def test_config_proxy(self): config = ConfigDict() config.set(b'http', b'proxy', b'http://localhost:3128/') manager = default_urllib3_manager(config=config) self.assertIsInstance(manager, urllib3.ProxyManager) self.assertTrue(hasattr(manager, 'proxy')) self.assertEqual(manager.proxy.scheme, 'http') self.assertEqual(manager.proxy.host, 'localhost') self.assertEqual(manager.proxy.port, 3128) def test_config_no_verify_ssl(self): manager = default_urllib3_manager(config=None, cert_reqs="CERT_NONE") self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') class SubprocessSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = SubprocessSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345') def test_run_command_password_and_privkey(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') def test_run_command_with_port_username_and_privkey(self): expected = ['ssh', '-x', '-p', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = SubprocessSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class PLinkSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = PLinkSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password_and_privkey(self): vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command( 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-pw', '12345', '-i', '/tmp/id_rsa', 'host', 'git-clone-url'] self.assertListEqual(expected, args[0]) def test_run_command_password(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + ['-pw', '12345', 'host', 'git-clone-url'] vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command('host', 'git-clone-url', password='12345') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args self.assertListEqual(expected, args[0]) def test_run_command_with_port_username_and_privkey(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-P', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = PLinkSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class RsyncUrlTests(TestCase): def test_simple(self): self.assertEqual( parse_rsync_url('foo:bar/path'), (None, 'foo', 'bar/path')) self.assertEqual( parse_rsync_url('user@foo:bar/path'), ('user', 'foo', 'bar/path')) def test_path(self): self.assertRaises(ValueError, parse_rsync_url, '/path') class CheckWantsTests(TestCase): def test_fine(self): check_wants( [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) def test_missing(self): self.assertRaises( InvalidWants, check_wants, [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) def test_annotated(self): self.assertRaises( InvalidWants, check_wants, [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262', b'refs/heads/blah^{}': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'})