diff --git a/dulwich/client.py b/dulwich/client.py index 07e127b0..5fbdcb8c 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1303 +1,1303 @@ # 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 dulwich 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 urllib2 import urlparse except ImportError: import urllib.request as urllib2 import urllib.parse as urlparse from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, UpdateRefsError, ) from dulwich.protocol import ( _RBUFSIZE, capability_agent, CAPABILITY_DELETE_REFS, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITIES_REF, 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, ) from dulwich.pack import ( write_pack_objects, ) from dulwich.refs import ( read_info_refs, ) def _fileno_can_read(fileno): """Check if a file descriptor is readable.""" return len(select.select([fileno], [], [], 0)[0]) > 0 COMMON_CAPABILITIES = [CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K] FETCH_CAPABILITIES = ([CAPABILITY_THIN_PACK, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED] + COMMON_CAPABILITIES) SEND_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([ ref.decode('ascii') for ref in ref_status if ref 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) if server_capabilities is None: (ref, server_capabilities) = extract_capabilities(ref) refs[ref] = sha if len(refs) == 0: return None, set([]) if refs == {CAPABILITIES_REF: ZERO_SHA}: refs = {} return refs, set(server_capabilities) # 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(FETCH_CAPABILITIES) self._fetch_capabilities.add(capability_agent()) self._send_capabilities = set(SEND_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, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects to upload. :param progress: Optional progress function :param write_pack: Function called with (file, iterable of objects) to write the objects returned by generate_pack_contents to the server. :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): """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 :param progress: Optional progress function :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) except: abort() raise else: commit() return result def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=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) :return: Dictionary with all remote refs (not just those fetched) """ 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([ref for ref in ref_status if ref 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 _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 b"side-band-64k" in capabilities: if progress is None: progress = lambda x: None 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 _handle_upload_pack_head(self, proto, capabilities, graph_walker, wants, can_read): """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 """ 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') 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 progress = lambda x: None 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) 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, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects to upload. :param progress: Optional callback called with progress updates :param write_pack: Function called with (file, iterable of objects) to write the objects returned by generate_pack_contents to the server. :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 = self._connect(b'receive-pack', path) with proto: old_refs, server_capabilities = read_pkt_refs(proto) negotiated_capabilities = self._send_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 = determine_wants(dict(old_refs)) except: proto.write_pkt_line(None) raise if not CAPABILITY_DELETE_REFS 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 objects = generate_pack_contents(have, want) dowrite = len(objects) > 0 dowrite = dowrite or any(old_refs.get(ref) != sha for (ref, sha) in new_refs.items() if sha != ZERO_SHA) if dowrite: write_pack(proto.write_file(), objects) self._handle_receive_pack_tail( proto, negotiated_capabilities, progress) return new_refs def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=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) :return: Dictionary with all remote refs (not just those fetched) """ proto, can_read = self._connect(b'upload-pack', path) with proto: refs, server_capabilities = read_pkt_refs(proto) negotiated_capabilities = ( self._fetch_capabilities & server_capabilities) if refs is None: proto.write_pkt_line(None) return refs try: wants = determine_wants(refs) except: 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 refs self._handle_upload_pack_head( proto, negotiated_capabilities, graph_walker, wants, can_read) self._handle_upload_pack_tail( proto, negotiated_capabilities, graph_walker, pack_data, progress) return refs def get_refs(self, path): """Retrieve the current refs from a git smart server.""" # stock `git ls-remote` uses upload-pack proto, _ = self._connect(b'upload-pack', path) with proto: refs, _ = read_pkt_refs(proto) return refs def archive(self, path, committish, write_data, progress=None, write_error=None): proto, can_read = self._connect(b'upload-archive', path) with proto: proto.write_pkt_line(b"argument " + committish) proto.write_pkt_line(None) pkt = proto.read_pkt_line() if pkt == b"NACK\n": return elif pkt == b"ACK\n": pass elif pkt.startswith(b"ERR "): raise GitProtocolError(pkt[4:].rstrip(b"\n")) 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 type(cmd) is not bytes: + if not isinstance(cmd, bytes): raise TypeError(cmd) - if type(path) is not bytes: + 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 err: 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) 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 def can_read(self): if sys.platform == 'win32': from msvcrt import get_osfhandle from win32pipe import PeekNamedPipe handle = get_osfhandle(self.proc.stdout.fileno()) data, total_bytes_avail, msg_bytes_left = PeekNamedPipe(handle, 0) return total_bytes_avail != 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.""" def __init__(self, **kwargs): self._connection = None self._stderr = None self._stderr = kwargs.get('stderr') if 'stderr' in kwargs: del kwargs['stderr'] super(SubprocessGitClient, self).__init__(**kwargs) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) git_command = None def _connect(self, service, path): - if type(service) is not bytes: + if not isinstance(service, bytes): raise TypeError(service) - if type(path) is not bytes: + if not isinstance(path, bytes): path = path.encode(self._remote_path_encoding) if self.git_command is None: git_command = find_git_command() argv = git_command + [service.decode('ascii'), path] p = SubprocessWrapper( subprocess.Popen(argv, bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=self._stderr)) return Protocol(p.read, p.write, p.close, report_activity=self._report_activity), p.can_read class LocalGitClient(GitClient): """Git Client that just uses a local Repo.""" def __init__(self, thin_packs=True, report_activity=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, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects to upload. :param progress: Optional progress function :param write_pack: Function called with (file, iterable of objects) to write the objects returned by generate_pack_contents to the server. :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: progress = lambda x: None with self._open_repo(path) as target: old_refs = target.get_refs() new_refs = determine_wants(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 not new_sha1 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_objects(generate_pack_contents(have, want)) 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): """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 :param progress: Optional progress function :return: Dictionary with all remote refs (not just those fetched) """ with self._open_repo(path) as r: return r.fetch(target, determine_wants=determine_wants, progress=progress) def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=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) :return: Dictionary with all remote refs (not just those fetched) """ with self._open_repo(path) as r: objects_iter = r.fetch_objects(determine_wants, graph_walker, progress) # 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 write_pack_objects(ProtocolFile(None, pack_data), objects_iter) return r.get_refs() 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): # 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) def run_command(self, host, command, username=None, port=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 """ raise NotImplementedError(self.run_command) class SubprocessSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'ssh' command.""" def run_command(self, host, command, username=None, port=None): if not isinstance(command, bytes): raise TypeError(command) #FIXME: This has no way to deal with passwords.. args = ['ssh', '-x'] if port is not None: args.extend(['-p', str(port)]) if username is not None: host = '%s@%s' % (username, host) args.append(host) proc = subprocess.Popen(args + [command], stdin=subprocess.PIPE, stdout=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, **kwargs): self.host = host self.port = port self.username = username 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 type(cmd) is not bytes: + if not isinstance(cmd, bytes): raise TypeError(cmd) - if type(path) is not bytes: + if not isinstance(path, bytes): path = path.encode(self._remote_path_encoding) if path.startswith(b"/~"): path = path[1:] argv = self._get_cmd_path(cmd) + b" '" + path + b"'" con = self.ssh_vendor.run_command( self.host, argv, port=self.port, username=self.username) return (Protocol(con.read, con.write, con.close, report_activity=self._report_activity), con.can_read) def default_user_agent_string(): return "dulwich/%s" % ".".join([str(x) for x in dulwich.__version__]) def default_urllib2_opener(config): if config is not None: proxy_server = config.get("http", "proxy") else: proxy_server = None handlers = [] if proxy_server is not None: handlers.append(urllib2.ProxyHandler({"http": proxy_server})) opener = urllib2.build_opener(*handlers) if config is not None: user_agent = config.get("http", "useragent") else: user_agent = None if user_agent is None: user_agent = default_user_agent_string() opener.addheaders = [('User-agent', user_agent)] return opener class HttpGitClient(GitClient): def __init__(self, base_url, dumb=None, opener=None, config=None, username=None, password=None, **kwargs): self._base_url = base_url.rstrip("/") + "/" self._username = username self._password = password self.dumb = dumb if opener is None: self.opener = default_urllib2_opener(config) else: self.opener = opener if username is not None: pass_man = urllib2.HTTPPasswordMgrWithDefaultRealm() pass_man.add_password(None, base_url, username, password) self.opener.add_handler(urllib2.HTTPBasicAuthHandler(pass_man)) GitClient.__init__(self, **kwargs) def get_url(self, path): return self._get_url(path).rstrip("/") @classmethod def from_parsedurl(cls, parsedurl, **kwargs): auth, host = urllib2.splituser(parsedurl.netloc) password = parsedurl.password if password is not None: password = urlunquote(password) username = parsedurl.username if username is not None: username = urlunquote(username) # TODO(jelmer): This also strips the username parsedurl = parsedurl._replace(netloc=host) return cls(urlparse.urlunparse(parsedurl), password=password, username=username, **kwargs) def __repr__(self): return "%s(%r, dumb=%r)" % (type(self).__name__, self._base_url, self.dumb) def _get_url(self, path): return urlparse.urljoin(self._base_url, path).rstrip("/") + "/" def _http_request(self, url, headers={}, data=None): req = urllib2.Request(url, headers=headers, data=data) try: resp = self.opener.open(req) except urllib2.HTTPError as e: if e.code == 404: raise NotGitRepository() if e.code != 200: raise GitProtocolError("unexpected http response %d" % e.code) return resp def _discover_references(self, service, url): assert url[-1] == "/" url = urlparse.urljoin(url, "info/refs") headers = {} if self.dumb is not False: url += "?service=%s" % service.decode('ascii') headers["Content-Type"] = "application/x-%s-request" % ( service.decode('ascii')) resp = self._http_request(url, headers) try: content_type = resp.info().gettype() except AttributeError: content_type = resp.info().get_content_type() try: self.dumb = (not content_type.startswith("application/x-git-")) if not self.dumb: proto = Protocol(resp.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) else: return read_info_refs(resp), set() finally: resp.close() def _smart_request(self, service, url, data): assert url[-1] == "/" url = urlparse.urljoin(url, service) headers = { "Content-Type": "application/x-%s-request" % service } resp = self._http_request(url, headers, data) try: content_type = resp.info().gettype() except AttributeError: content_type = resp.info().get_content_type() if content_type != ( "application/x-%s-result" % service): raise GitProtocolError("Invalid content-type from server: %s" % content_type) return resp def send_pack(self, path, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects to upload. :param progress: Optional progress function :param write_pack: Function called with (file, iterable of objects) to write the objects returned by generate_pack_contents to the server. :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 = self._discover_references( b"git-receive-pack", url) negotiated_capabilities = self._send_capabilities & server_capabilities if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() new_refs = determine_wants(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 objects = generate_pack_contents(have, want) if len(objects) > 0: write_pack(req_proto.write_file(), objects) resp = self._smart_request("git-receive-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(resp.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, progress=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) :return: Dictionary with all remote refs (not just those fetched) """ url = self._get_url(path) refs, server_capabilities = self._discover_references( b"git-upload-pack", url) negotiated_capabilities = self._fetch_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 refs if self.dumb: raise NotImplementedError(self.send_pack) req_data = BytesIO() req_proto = Protocol(None, req_data.write) self._handle_upload_pack_head( req_proto, negotiated_capabilities, graph_walker, wants, lambda: False) resp = self._smart_request( "git-upload-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(resp.read, None) self._handle_upload_pack_tail(resp_proto, negotiated_capabilities, graph_walker, pack_data, progress) return refs 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'): path = parsed.path if path.startswith('/'): path = parsed.path[1:] return SSHGitClient.from_parsedurl(parsed, **kwargs), 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 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 if ':' in location and not '@' in location: # SSH with no user@, zero or one leading slash. (hostname, path) = location.split(':', 1) return SSHGitClient(hostname, **kwargs), path 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 return SSHGitClient(host, username=user, **kwargs), path # Otherwise, assume it's a local path. return default_local_git_client_cls(**kwargs), location diff --git a/dulwich/pack.py b/dulwich/pack.py index 54af2e03..878162b9 100644 --- a/dulwich/pack.py +++ b/dulwich/pack.py @@ -1,1965 +1,1963 @@ # pack.py -- For dealing with packed git objects. # 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. # """Classes for dealing with packed git objects. A pack is a compact representation of a bunch of objects, stored using deltas where possible. They have two parts, the pack file, which stores the data, and an index that tells you where the data is. To find an object you look in all of the index files 'til you find a match for the object name. You then use the pointer got from this as a pointer in to the corresponding packfile. """ from collections import defaultdict import binascii from io import BytesIO, UnsupportedOperation from collections import ( deque, ) import difflib import struct from itertools import chain try: from itertools import imap, izip except ImportError: # Python3 imap = map izip = zip import os import sys try: import mmap except ImportError: has_mmap = False else: has_mmap = True # For some reason the above try, except fails to set has_mmap = False for plan9 if sys.platform == 'Plan9': has_mmap = False from hashlib import sha1 from os import ( SEEK_CUR, SEEK_END, ) from struct import unpack_from import zlib from dulwich.errors import ( ApplyDeltaError, ChecksumMismatch, ) from dulwich.file import GitFile from dulwich.lru_cache import ( LRUSizeCache, ) from dulwich.objects import ( ShaFile, hex_to_sha, sha_to_hex, object_header, ) OFS_DELTA = 6 REF_DELTA = 7 DELTA_TYPES = (OFS_DELTA, REF_DELTA) DEFAULT_PACK_DELTA_WINDOW_SIZE = 10 def take_msb_bytes(read, crc32=None): """Read bytes marked with most significant bit. :param read: Read function """ ret = [] while len(ret) == 0 or ret[-1] & 0x80: b = read(1) if crc32 is not None: crc32 = binascii.crc32(b, crc32) ret.append(ord(b[:1])) return ret, crc32 class UnpackedObject(object): """Class encapsulating an object unpacked from a pack file. These objects should only be created from within unpack_object. Most members start out as empty and are filled in at various points by read_zlib_chunks, unpack_object, DeltaChainIterator, etc. End users of this object should take care that the function they're getting this object from is guaranteed to set the members they need. """ __slots__ = [ 'offset', # Offset in its pack. '_sha', # Cached binary SHA. 'obj_type_num', # Type of this object. 'obj_chunks', # Decompressed and delta-resolved chunks. 'pack_type_num', # Type of this object in the pack (may be a delta). 'delta_base', # Delta base offset or SHA. 'comp_chunks', # Compressed object chunks. 'decomp_chunks', # Decompressed object chunks. 'decomp_len', # Decompressed length of this object. 'crc32', # CRC32. ] # TODO(dborowitz): read_zlib_chunks and unpack_object could very well be # methods of this object. def __init__(self, pack_type_num, delta_base, decomp_len, crc32): self.offset = None self._sha = None self.pack_type_num = pack_type_num self.delta_base = delta_base self.comp_chunks = None self.decomp_chunks = [] self.decomp_len = decomp_len self.crc32 = crc32 if pack_type_num in DELTA_TYPES: self.obj_type_num = None self.obj_chunks = None else: self.obj_type_num = pack_type_num self.obj_chunks = self.decomp_chunks self.delta_base = delta_base def sha(self): """Return the binary SHA of this object.""" if self._sha is None: self._sha = obj_sha(self.obj_type_num, self.obj_chunks) return self._sha def sha_file(self): """Return a ShaFile from this object.""" return ShaFile.from_raw_chunks(self.obj_type_num, self.obj_chunks) # Only provided for backwards compatibility with code that expects either # chunks or a delta tuple. def _obj(self): """Return the decompressed chunks, or (delta base, delta chunks).""" if self.pack_type_num in DELTA_TYPES: return (self.delta_base, self.decomp_chunks) else: return self.decomp_chunks def __eq__(self, other): if not isinstance(other, UnpackedObject): return False for slot in self.__slots__: if getattr(self, slot) != getattr(other, slot): return False return True def __ne__(self, other): return not (self == other) def __repr__(self): data = ['%s=%r' % (s, getattr(self, s)) for s in self.__slots__] return '%s(%s)' % (self.__class__.__name__, ', '.join(data)) _ZLIB_BUFSIZE = 4096 def read_zlib_chunks(read_some, unpacked, include_comp=False, buffer_size=_ZLIB_BUFSIZE): """Read zlib data from a buffer. This function requires that the buffer have additional data following the compressed data, which is guaranteed to be the case for git pack files. :param read_some: Read function that returns at least one byte, but may return less than the requested size. :param unpacked: An UnpackedObject to write result data to. If its crc32 attr is not None, the CRC32 of the compressed bytes will be computed using this starting CRC32. After this function, will have the following attrs set: * comp_chunks (if include_comp is True) * decomp_chunks * decomp_len * crc32 :param include_comp: If True, include compressed data in the result. :param buffer_size: Size of the read buffer. :return: Leftover unused data from the decompression. :raise zlib.error: if a decompression error occurred. """ if unpacked.decomp_len <= -1: raise ValueError('non-negative zlib data stream size expected') decomp_obj = zlib.decompressobj() comp_chunks = [] decomp_chunks = unpacked.decomp_chunks decomp_len = 0 crc32 = unpacked.crc32 while True: add = read_some(buffer_size) if not add: raise zlib.error('EOF before end of zlib stream') comp_chunks.append(add) decomp = decomp_obj.decompress(add) decomp_len += len(decomp) decomp_chunks.append(decomp) unused = decomp_obj.unused_data if unused: left = len(unused) if crc32 is not None: crc32 = binascii.crc32(add[:-left], crc32) if include_comp: comp_chunks[-1] = add[:-left] break elif crc32 is not None: crc32 = binascii.crc32(add, crc32) if crc32 is not None: crc32 &= 0xffffffff if decomp_len != unpacked.decomp_len: raise zlib.error('decompressed data does not match expected size') unpacked.crc32 = crc32 if include_comp: unpacked.comp_chunks = comp_chunks return unused def iter_sha1(iter): """Return the hexdigest of the SHA1 over a set of names. :param iter: Iterator over string objects :return: 40-byte hex sha1 digest """ sha = sha1() for name in iter: sha.update(name) return sha.hexdigest().encode('ascii') def load_pack_index(path): """Load an index file by path. :param filename: Path to the index file :return: A PackIndex loaded from the given path """ with GitFile(path, 'rb') as f: return load_pack_index_file(path, f) def _load_file_contents(f, size=None): try: fd = f.fileno() except (UnsupportedOperation, AttributeError): fd = None # Attempt to use mmap if possible if fd is not None: if size is None: size = os.fstat(fd).st_size if has_mmap: try: contents = mmap.mmap(fd, size, access=mmap.ACCESS_READ) except mmap.error: # Perhaps a socket? pass else: return contents, size contents = f.read() size = len(contents) return contents, size def load_pack_index_file(path, f): """Load an index file from a file-like object. :param path: Path for the index file :param f: File-like object :return: A PackIndex loaded from the given file """ contents, size = _load_file_contents(f) if contents[:4] == b'\377tOc': version = struct.unpack(b'>L', contents[4:8])[0] if version == 2: return PackIndex2(path, file=f, contents=contents, size=size) else: raise KeyError('Unknown pack index format %d' % version) else: return PackIndex1(path, file=f, contents=contents, size=size) def bisect_find_sha(start, end, sha, unpack_name): """Find a SHA in a data blob with sorted SHAs. :param start: Start index of range to search :param end: End index of range to search :param sha: Sha to find :param unpack_name: Callback to retrieve SHA by index :return: Index of the SHA, or None if it wasn't found """ assert start <= end while start <= end: i = (start + end) // 2 file_sha = unpack_name(i) if file_sha < sha: start = i + 1 elif file_sha > sha: end = i - 1 else: return i return None class PackIndex(object): """An index in to a packfile. Given a sha id of an object a pack index can tell you the location in the packfile of that object if it has it. """ def __eq__(self, other): if not isinstance(other, PackIndex): return False for (name1, _, _), (name2, _, _) in izip(self.iterentries(), other.iterentries()): if name1 != name2: return False return True def __ne__(self, other): return not self.__eq__(other) def __len__(self): """Return the number of entries in this pack index.""" raise NotImplementedError(self.__len__) def __iter__(self): """Iterate over the SHAs in this pack.""" return imap(sha_to_hex, self._itersha()) def iterentries(self): """Iterate over the entries in this pack index. :return: iterator over tuples with object name, offset in packfile and crc32 checksum. """ raise NotImplementedError(self.iterentries) def get_pack_checksum(self): """Return the SHA1 checksum stored for the corresponding packfile. :return: 20-byte binary digest """ raise NotImplementedError(self.get_pack_checksum) def object_index(self, sha): """Return the index in to the corresponding packfile for the object. Given the name of an object it will return the offset that object lives at within the corresponding pack file. If the pack file doesn't have the object then None will be returned. """ if len(sha) == 40: sha = hex_to_sha(sha) return self._object_index(sha) def _object_index(self, sha): """See object_index. :param sha: A *binary* SHA string. (20 characters long)_ """ raise NotImplementedError(self._object_index) def objects_sha1(self): """Return the hex SHA1 over all the shas of all objects in this pack. :note: This is used for the filename of the pack. """ return iter_sha1(self._itersha()) def _itersha(self): """Yield all the SHA1's of the objects in the index, sorted.""" raise NotImplementedError(self._itersha) class MemoryPackIndex(PackIndex): """Pack index that is stored entirely in memory.""" def __init__(self, entries, pack_checksum=None): """Create a new MemoryPackIndex. :param entries: Sequence of name, idx, crc32 (sorted) :param pack_checksum: Optional pack checksum """ self._by_sha = {} for name, idx, crc32 in entries: self._by_sha[name] = idx self._entries = entries self._pack_checksum = pack_checksum def get_pack_checksum(self): return self._pack_checksum def __len__(self): return len(self._entries) def _object_index(self, sha): return self._by_sha[sha][0] def _itersha(self): return iter(self._by_sha) def iterentries(self): return iter(self._entries) class FilePackIndex(PackIndex): """Pack index that is based on a file. To do the loop it opens the file, and indexes first 256 4 byte groups with the first byte of the sha id. The value in the four byte group indexed is the end of the group that shares the same starting byte. Subtract one from the starting byte and index again to find the start of the group. The values are sorted by sha id within the group, so do the math to find the start and end offset and then bisect in to find if the value is present. """ def __init__(self, filename, file=None, contents=None, size=None): """Create a pack index object. Provide it with the name of the index file to consider, and it will map it whenever required. """ self._filename = filename # Take the size now, so it can be checked each time we map the file to # ensure that it hasn't changed. if file is None: self._file = GitFile(filename, 'rb') else: self._file = file if contents is None: self._contents, self._size = _load_file_contents(self._file, size) else: self._contents, self._size = (contents, size) def __eq__(self, other): # Quick optimization: if (isinstance(other, FilePackIndex) and self._fan_out_table != other._fan_out_table): return False return super(FilePackIndex, self).__eq__(other) def close(self): self._file.close() if getattr(self._contents, "close", None) is not None: self._contents.close() def __len__(self): """Return the number of entries in this pack index.""" return self._fan_out_table[-1] def _unpack_entry(self, i): """Unpack the i-th entry in the index file. :return: Tuple with object name (SHA), offset in pack file and CRC32 checksum (if known). """ raise NotImplementedError(self._unpack_entry) def _unpack_name(self, i): """Unpack the i-th name from the index file.""" raise NotImplementedError(self._unpack_name) def _unpack_offset(self, i): """Unpack the i-th object offset from the index file.""" raise NotImplementedError(self._unpack_offset) def _unpack_crc32_checksum(self, i): """Unpack the crc32 checksum for the i-th object from the index file.""" raise NotImplementedError(self._unpack_crc32_checksum) def _itersha(self): for i in range(len(self)): yield self._unpack_name(i) def iterentries(self): """Iterate over the entries in this pack index. :return: iterator over tuples with object name, offset in packfile and crc32 checksum. """ for i in range(len(self)): yield self._unpack_entry(i) def _read_fan_out_table(self, start_offset): ret = [] for i in range(0x100): fanout_entry = self._contents[start_offset+i*4:start_offset+(i+1)*4] ret.append(struct.unpack('>L', fanout_entry)[0]) return ret def check(self): """Check that the stored checksum matches the actual checksum.""" actual = self.calculate_checksum() stored = self.get_stored_checksum() if actual != stored: raise ChecksumMismatch(stored, actual) def calculate_checksum(self): """Calculate the SHA1 checksum over this pack index. :return: This is a 20-byte binary digest """ return sha1(self._contents[:-20]).digest() def get_pack_checksum(self): """Return the SHA1 checksum stored for the corresponding packfile. :return: 20-byte binary digest """ return bytes(self._contents[-40:-20]) def get_stored_checksum(self): """Return the SHA1 checksum stored for this index. :return: 20-byte binary digest """ return bytes(self._contents[-20:]) def _object_index(self, sha): """See object_index. :param sha: A *binary* SHA string. (20 characters long)_ """ assert len(sha) == 20 idx = ord(sha[:1]) if idx == 0: start = 0 else: start = self._fan_out_table[idx-1] end = self._fan_out_table[idx] i = bisect_find_sha(start, end, sha, self._unpack_name) if i is None: raise KeyError(sha) return self._unpack_offset(i) class PackIndex1(FilePackIndex): """Version 1 Pack Index file.""" def __init__(self, filename, file=None, contents=None, size=None): super(PackIndex1, self).__init__(filename, file, contents, size) self.version = 1 self._fan_out_table = self._read_fan_out_table(0) def _unpack_entry(self, i): (offset, name) = unpack_from('>L20s', self._contents, (0x100 * 4) + (i * 24)) return (name, offset, None) def _unpack_name(self, i): offset = (0x100 * 4) + (i * 24) + 4 return self._contents[offset:offset+20] def _unpack_offset(self, i): offset = (0x100 * 4) + (i * 24) return unpack_from('>L', self._contents, offset)[0] def _unpack_crc32_checksum(self, i): # Not stored in v1 index files return None class PackIndex2(FilePackIndex): """Version 2 Pack Index file.""" def __init__(self, filename, file=None, contents=None, size=None): super(PackIndex2, self).__init__(filename, file, contents, size) if self._contents[:4] != b'\377tOc': raise AssertionError('Not a v2 pack index file') (self.version, ) = unpack_from(b'>L', self._contents, 4) if self.version != 2: raise AssertionError('Version was %d' % self.version) self._fan_out_table = self._read_fan_out_table(8) self._name_table_offset = 8 + 0x100 * 4 self._crc32_table_offset = self._name_table_offset + 20 * len(self) self._pack_offset_table_offset = (self._crc32_table_offset + 4 * len(self)) self._pack_offset_largetable_offset = (self._pack_offset_table_offset + 4 * len(self)) def _unpack_entry(self, i): return (self._unpack_name(i), self._unpack_offset(i), self._unpack_crc32_checksum(i)) def _unpack_name(self, i): offset = self._name_table_offset + i * 20 return self._contents[offset:offset+20] def _unpack_offset(self, i): offset = self._pack_offset_table_offset + i * 4 offset = unpack_from('>L', self._contents, offset)[0] if offset & (2**31): offset = self._pack_offset_largetable_offset + (offset&(2**31-1)) * 8 offset = unpack_from('>Q', self._contents, offset)[0] return offset def _unpack_crc32_checksum(self, i): return unpack_from('>L', self._contents, self._crc32_table_offset + i * 4)[0] def read_pack_header(read): """Read the header of a pack file. :param read: Read function :return: Tuple of (pack version, number of objects). If no data is available to read, returns (None, None). """ header = read(12) if not header: return None, None if header[:4] != b'PACK': raise AssertionError('Invalid pack header %r' % header) (version,) = unpack_from(b'>L', header, 4) if version not in (2, 3): raise AssertionError('Version was %d' % version) (num_objects,) = unpack_from(b'>L', header, 8) return (version, num_objects) def chunks_length(chunks): if isinstance(chunks, bytes): return len(chunks) else: return sum(imap(len, chunks)) def unpack_object(read_all, read_some=None, compute_crc32=False, include_comp=False, zlib_bufsize=_ZLIB_BUFSIZE): """Unpack a Git object. :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. :param compute_crc32: If True, compute the CRC32 of the compressed data. If False, the returned CRC32 will be None. :param include_comp: If True, include compressed data in the result. :param zlib_bufsize: An optional buffer size for zlib operations. :return: A tuple of (unpacked, unused), where unused is the unused data leftover from decompression, and unpacked in an UnpackedObject with the following attrs set: * obj_chunks (for non-delta types) * pack_type_num * delta_base (for delta types) * comp_chunks (if include_comp is True) * decomp_chunks * decomp_len * crc32 (if compute_crc32 is True) """ if read_some is None: read_some = read_all if compute_crc32: crc32 = 0 else: crc32 = None bytes, crc32 = take_msb_bytes(read_all, crc32=crc32) type_num = (bytes[0] >> 4) & 0x07 size = bytes[0] & 0x0f for i, byte in enumerate(bytes[1:]): size += (byte & 0x7f) << ((i * 7) + 4) raw_base = len(bytes) if type_num == OFS_DELTA: bytes, crc32 = take_msb_bytes(read_all, crc32=crc32) raw_base += len(bytes) if bytes[-1] & 0x80: raise AssertionError delta_base_offset = bytes[0] & 0x7f for byte in bytes[1:]: delta_base_offset += 1 delta_base_offset <<= 7 delta_base_offset += (byte & 0x7f) delta_base = delta_base_offset elif type_num == REF_DELTA: delta_base = read_all(20) if compute_crc32: crc32 = binascii.crc32(delta_base, crc32) raw_base += 20 else: delta_base = None unpacked = UnpackedObject(type_num, delta_base, size, crc32) unused = read_zlib_chunks(read_some, unpacked, buffer_size=zlib_bufsize, include_comp=include_comp) return unpacked, unused def _compute_object_size(value): """Compute the size of a unresolved object for use with LRUSizeCache.""" (num, obj) = value if num in DELTA_TYPES: return chunks_length(obj[1]) return chunks_length(obj) class PackStreamReader(object): """Class to read a pack stream. The pack is read from a ReceivableProtocol using read() or recv() as appropriate. """ def __init__(self, read_all, read_some=None, zlib_bufsize=_ZLIB_BUFSIZE): self.read_all = read_all if read_some is None: self.read_some = read_all else: self.read_some = read_some self.sha = sha1() self._offset = 0 self._rbuf = BytesIO() # trailer is a deque to avoid memory allocation on small reads self._trailer = deque() self._zlib_bufsize = zlib_bufsize def _read(self, read, size): """Read up to size bytes using the given callback. As a side effect, update the verifier's hash (excluding the last 20 bytes read). :param read: The read callback to read from. :param size: The maximum number of bytes to read; the particular behavior is callback-specific. """ data = read(size) # maintain a trailer of the last 20 bytes we've read n = len(data) self._offset += n tn = len(self._trailer) if n >= 20: to_pop = tn to_add = 20 else: to_pop = max(n + tn - 20, 0) to_add = n self.sha.update(bytes(bytearray([self._trailer.popleft() for _ in range(to_pop)]))) self._trailer.extend(data[-to_add:]) # hash everything but the trailer self.sha.update(data[:-to_add]) return data def _buf_len(self): buf = self._rbuf start = buf.tell() buf.seek(0, SEEK_END) end = buf.tell() buf.seek(start) return end - start @property def offset(self): return self._offset - self._buf_len() def read(self, size): """Read, blocking until size bytes are read.""" buf_len = self._buf_len() if buf_len >= size: return self._rbuf.read(size) buf_data = self._rbuf.read() self._rbuf = BytesIO() return buf_data + self._read(self.read_all, size - buf_len) def recv(self, size): """Read up to size bytes, blocking until one byte is read.""" buf_len = self._buf_len() if buf_len: data = self._rbuf.read(size) if size >= buf_len: self._rbuf = BytesIO() return data return self._read(self.read_some, size) def __len__(self): return self._num_objects def read_objects(self, compute_crc32=False): """Read the objects in this pack file. :param compute_crc32: If True, compute the CRC32 of the compressed data. If False, the returned CRC32 will be None. :return: Iterator over UnpackedObjects with the following members set: offset obj_type_num obj_chunks (for non-delta types) delta_base (for delta types) decomp_chunks decomp_len crc32 (if compute_crc32 is True) :raise ChecksumMismatch: if the checksum of the pack contents does not match the checksum in the pack trailer. :raise zlib.error: if an error occurred during zlib decompression. :raise IOError: if an error occurred writing to the output file. """ pack_version, self._num_objects = read_pack_header(self.read) if pack_version is None: return for i in range(self._num_objects): offset = self.offset unpacked, unused = unpack_object( self.read, read_some=self.recv, compute_crc32=compute_crc32, zlib_bufsize=self._zlib_bufsize) unpacked.offset = offset # prepend any unused data to current read buffer buf = BytesIO() buf.write(unused) buf.write(self._rbuf.read()) buf.seek(0) self._rbuf = buf yield unpacked if self._buf_len() < 20: # If the read buffer is full, then the last read() got the whole # trailer off the wire. If not, it means there is still some of the # trailer to read. We need to read() all 20 bytes; N come from the # read buffer and (20 - N) come from the wire. self.read(20) pack_sha = bytearray(self._trailer) if pack_sha != self.sha.digest(): raise ChecksumMismatch(sha_to_hex(pack_sha), self.sha.hexdigest()) class PackStreamCopier(PackStreamReader): """Class to verify a pack stream as it is being read. The pack is read from a ReceivableProtocol using read() or recv() as appropriate and written out to the given file-like object. """ def __init__(self, read_all, read_some, outfile, delta_iter=None): """Initialize the copier. :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. :param outfile: File-like object to write output through. :param delta_iter: Optional DeltaChainIterator to record deltas as we read them. """ super(PackStreamCopier, self).__init__(read_all, read_some=read_some) self.outfile = outfile self._delta_iter = delta_iter def _read(self, read, size): """Read data from the read callback and write it to the file.""" data = super(PackStreamCopier, self)._read(read, size) self.outfile.write(data) return data def verify(self): """Verify a pack stream and write it to the output file. See PackStreamReader.iterobjects for a list of exceptions this may throw. """ if self._delta_iter: for unpacked in self.read_objects(): self._delta_iter.record(unpacked) else: for _ in self.read_objects(): pass def obj_sha(type, chunks): """Compute the SHA for a numeric type and object chunks.""" sha = sha1() sha.update(object_header(type, chunks_length(chunks))) if isinstance(chunks, bytes): sha.update(chunks) else: for chunk in chunks: sha.update(chunk) return sha.digest() def compute_file_sha(f, start_ofs=0, end_ofs=0, buffer_size=1<<16): """Hash a portion of a file into a new SHA. :param f: A file-like object to read from that supports seek(). :param start_ofs: The offset in the file to start reading at. :param end_ofs: The offset in the file to end reading at, relative to the end of the file. :param buffer_size: A buffer size for reading. :return: A new SHA object updated with data read from the file. """ sha = sha1() f.seek(0, SEEK_END) length = f.tell() if (end_ofs < 0 and length + end_ofs < start_ofs) or end_ofs > length: raise AssertionError( "Attempt to read beyond file length. " "start_ofs: %d, end_ofs: %d, file length: %d" % ( start_ofs, end_ofs, length)) todo = length + end_ofs - start_ofs f.seek(start_ofs) while todo: data = f.read(min(todo, buffer_size)) sha.update(data) todo -= len(data) return sha class PackData(object): """The data contained in a packfile. Pack files can be accessed both sequentially for exploding a pack, and directly with the help of an index to retrieve a specific object. The objects within are either complete or a delta against another. The header is variable length. If the MSB of each byte is set then it indicates that the subsequent byte is still part of the header. For the first byte the next MS bits are the type, which tells you the type of object, and whether it is a delta. The LS byte is the lowest bits of the size. For each subsequent byte the LS 7 bits are the next MS bits of the size, i.e. the last byte of the header contains the MS bits of the size. For the complete objects the data is stored as zlib deflated data. The size in the header is the uncompressed object size, so to uncompress you need to just keep feeding data to zlib until you get an object back, or it errors on bad data. This is done here by just giving the complete buffer from the start of the deflated object on. This is bad, but until I get mmap sorted out it will have to do. Currently there are no integrity checks done. Also no attempt is made to try and detect the delta case, or a request for an object at the wrong position. It will all just throw a zlib or KeyError. """ def __init__(self, filename, file=None, size=None): """Create a PackData object representing the pack in the given filename. The file must exist and stay readable until the object is disposed of. It must also stay the same size. It will be mapped whenever needed. Currently there is a restriction on the size of the pack as the python mmap implementation is flawed. """ self._filename = filename self._size = size self._header_size = 12 if file is None: self._file = GitFile(self._filename, 'rb') else: self._file = file (version, self._num_objects) = read_pack_header(self._file.read) self._offset_cache = LRUSizeCache(1024*1024*20, compute_size=_compute_object_size) self.pack = None @property def filename(self): return os.path.basename(self._filename) @classmethod def from_file(cls, file, size): return cls(str(file), file=file, size=size) @classmethod def from_path(cls, path): return cls(filename=path) def close(self): self._file.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def _get_size(self): if self._size is not None: return self._size self._size = os.path.getsize(self._filename) if self._size < self._header_size: errmsg = ('%s is too small for a packfile (%d < %d)' % (self._filename, self._size, self._header_size)) raise AssertionError(errmsg) return self._size def __len__(self): """Returns the number of objects in this pack.""" return self._num_objects def calculate_checksum(self): """Calculate the checksum for this pack. :return: 20-byte binary SHA1 digest """ return compute_file_sha(self._file, end_ofs=-20).digest() def get_ref(self, sha): """Get the object for a ref SHA, only looking in this pack.""" # TODO: cache these results if self.pack is None: raise KeyError(sha) try: offset = self.pack.index.object_index(sha) except KeyError: offset = None if offset: type, obj = self.get_object_at(offset) elif self.pack is not None and self.pack.resolve_ext_ref: type, obj = self.pack.resolve_ext_ref(sha) else: raise KeyError(sha) return offset, type, obj def resolve_object(self, offset, type, obj, get_ref=None): """Resolve an object, possibly resolving deltas when necessary. :return: Tuple with object type and contents. """ # Walk down the delta chain, building a stack of deltas to reach # the requested object. base_offset = offset base_type = type base_obj = obj delta_stack = [] while base_type in DELTA_TYPES: prev_offset = base_offset if get_ref is None: get_ref = self.get_ref if base_type == OFS_DELTA: (delta_offset, delta) = base_obj # TODO: clean up asserts and replace with nicer error messages assert ( isinstance(base_offset, int) or isinstance(base_offset, long)) assert ( isinstance(delta_offset, int) or isinstance(base_offset, long)) base_offset = base_offset - delta_offset base_type, base_obj = self.get_object_at(base_offset) assert isinstance(base_type, int) elif base_type == REF_DELTA: (basename, delta) = base_obj assert isinstance(basename, bytes) and len(basename) == 20 base_offset, base_type, base_obj = get_ref(basename) assert isinstance(base_type, int) delta_stack.append((prev_offset, base_type, delta)) # Now grab the base object (mustn't be a delta) and apply the # deltas all the way up the stack. chunks = base_obj for prev_offset, delta_type, delta in reversed(delta_stack): chunks = apply_delta(chunks, delta) # TODO(dborowitz): This can result in poor performance if # large base objects are separated from deltas in the pack. # We should reorganize so that we apply deltas to all # objects in a chain one after the other to optimize cache # performance. if prev_offset is not None: self._offset_cache[prev_offset] = base_type, chunks return base_type, chunks def iterobjects(self, progress=None, compute_crc32=True): self._file.seek(self._header_size) for i in range(1, self._num_objects + 1): offset = self._file.tell() unpacked, unused = unpack_object( self._file.read, compute_crc32=compute_crc32) if progress is not None: progress(i, self._num_objects) yield (offset, unpacked.pack_type_num, unpacked._obj(), unpacked.crc32) self._file.seek(-len(unused), SEEK_CUR) # Back up over unused data. def _iter_unpacked(self): # TODO(dborowitz): Merge this with iterobjects, if we can change its # return type. self._file.seek(self._header_size) if self._num_objects is None: return for _ in range(self._num_objects): offset = self._file.tell() unpacked, unused = unpack_object( self._file.read, compute_crc32=False) unpacked.offset = offset yield unpacked self._file.seek(-len(unused), SEEK_CUR) # Back up over unused data. def iterentries(self, progress=None): """Yield entries summarizing the contents of this pack. :param progress: Progress function, called with current and total object count. :return: iterator of tuples with (sha, offset, crc32) """ num_objects = self._num_objects resolve_ext_ref = ( self.pack.resolve_ext_ref if self.pack is not None else None) indexer = PackIndexer.for_pack_data( self, resolve_ext_ref=resolve_ext_ref) for i, result in enumerate(indexer): if progress is not None: progress(i, num_objects) yield result def sorted_entries(self, progress=None): """Return entries in this pack, sorted by SHA. :param progress: Progress function, called with current and total object count :return: List of tuples with (sha, offset, crc32) """ - ret = list(self.iterentries(progress=progress)) - ret.sort() + ret = sorted(self.iterentries(progress=progress)) return ret def create_index_v1(self, filename, progress=None): """Create a version 1 file for this data file. :param filename: Index filename. :param progress: Progress report function :return: Checksum of index file """ entries = self.sorted_entries(progress=progress) with GitFile(filename, 'wb') as f: return write_pack_index_v1(f, entries, self.calculate_checksum()) def create_index_v2(self, filename, progress=None): """Create a version 2 index file for this data file. :param filename: Index filename. :param progress: Progress report function :return: Checksum of index file """ entries = self.sorted_entries(progress=progress) with GitFile(filename, 'wb') as f: return write_pack_index_v2(f, entries, self.calculate_checksum()) def create_index(self, filename, progress=None, version=2): """Create an index file for this data file. :param filename: Index filename. :param progress: Progress report function :return: Checksum of index file """ if version == 1: return self.create_index_v1(filename, progress) elif version == 2: return self.create_index_v2(filename, progress) else: raise ValueError('unknown index format %d' % version) def get_stored_checksum(self): """Return the expected checksum stored in this pack.""" self._file.seek(-20, SEEK_END) return self._file.read(20) def check(self): """Check the consistency of this pack.""" actual = self.calculate_checksum() stored = self.get_stored_checksum() if actual != stored: raise ChecksumMismatch(stored, actual) def get_object_at(self, offset): """Given an offset in to the packfile return the object that is there. Using the associated index the location of an object can be looked up, and then the packfile can be asked directly for that object using this function. """ try: return self._offset_cache[offset] except KeyError: pass assert offset >= self._header_size self._file.seek(offset) unpacked, _ = unpack_object(self._file.read) return (unpacked.pack_type_num, unpacked._obj()) class DeltaChainIterator(object): """Abstract iterator over pack data based on delta chains. Each object in the pack is guaranteed to be inflated exactly once, regardless of how many objects reference it as a delta base. As a result, memory usage is proportional to the length of the longest delta chain. Subclasses can override _result to define the result type of the iterator. By default, results are UnpackedObjects with the following members set: * offset * obj_type_num * obj_chunks * pack_type_num * delta_base (for delta types) * comp_chunks (if _include_comp is True) * decomp_chunks * decomp_len * crc32 (if _compute_crc32 is True) """ _compute_crc32 = False _include_comp = False def __init__(self, file_obj, resolve_ext_ref=None): self._file = file_obj self._resolve_ext_ref = resolve_ext_ref self._pending_ofs = defaultdict(list) self._pending_ref = defaultdict(list) self._full_ofs = [] self._shas = {} self._ext_refs = [] @classmethod def for_pack_data(cls, pack_data, resolve_ext_ref=None): walker = cls(None, resolve_ext_ref=resolve_ext_ref) walker.set_pack_data(pack_data) for unpacked in pack_data._iter_unpacked(): walker.record(unpacked) return walker def record(self, unpacked): type_num = unpacked.pack_type_num offset = unpacked.offset if type_num == OFS_DELTA: base_offset = offset - unpacked.delta_base self._pending_ofs[base_offset].append(offset) elif type_num == REF_DELTA: self._pending_ref[unpacked.delta_base].append(offset) else: self._full_ofs.append((offset, type_num)) def set_pack_data(self, pack_data): self._file = pack_data._file def _walk_all_chains(self): for offset, type_num in self._full_ofs: for result in self._follow_chain(offset, type_num, None): yield result for result in self._walk_ref_chains(): yield result assert not self._pending_ofs def _ensure_no_pending(self): if self._pending_ref: raise KeyError([sha_to_hex(s) for s in self._pending_ref]) def _walk_ref_chains(self): if not self._resolve_ext_ref: self._ensure_no_pending() return for base_sha, pending in sorted(self._pending_ref.items()): if base_sha not in self._pending_ref: continue try: type_num, chunks = self._resolve_ext_ref(base_sha) except KeyError: # Not an external ref, but may depend on one. Either it will get # popped via a _follow_chain call, or we will raise an error # below. continue self._ext_refs.append(base_sha) self._pending_ref.pop(base_sha) for new_offset in pending: for result in self._follow_chain(new_offset, type_num, chunks): yield result self._ensure_no_pending() def _result(self, unpacked): return unpacked def _resolve_object(self, offset, obj_type_num, base_chunks): self._file.seek(offset) unpacked, _ = unpack_object( self._file.read, include_comp=self._include_comp, compute_crc32=self._compute_crc32) unpacked.offset = offset if base_chunks is None: assert unpacked.pack_type_num == obj_type_num else: assert unpacked.pack_type_num in DELTA_TYPES unpacked.obj_type_num = obj_type_num unpacked.obj_chunks = apply_delta(base_chunks, unpacked.decomp_chunks) return unpacked def _follow_chain(self, offset, obj_type_num, base_chunks): # Unlike PackData.get_object_at, there is no need to cache offsets as # this approach by design inflates each object exactly once. todo = [(offset, obj_type_num, base_chunks)] for offset, obj_type_num, base_chunks in todo: unpacked = self._resolve_object(offset, obj_type_num, base_chunks) yield self._result(unpacked) unblocked = chain(self._pending_ofs.pop(unpacked.offset, []), self._pending_ref.pop(unpacked.sha(), [])) todo.extend( (new_offset, unpacked.obj_type_num, unpacked.obj_chunks) for new_offset in unblocked) def __iter__(self): return self._walk_all_chains() def ext_refs(self): return self._ext_refs class PackIndexer(DeltaChainIterator): """Delta chain iterator that yields index entries.""" _compute_crc32 = True def _result(self, unpacked): return unpacked.sha(), unpacked.offset, unpacked.crc32 class PackInflater(DeltaChainIterator): """Delta chain iterator that yields ShaFile objects.""" def _result(self, unpacked): return unpacked.sha_file() class SHA1Reader(object): """Wrapper around a file-like object that remembers the SHA1 of its data.""" def __init__(self, f): self.f = f self.sha1 = sha1(b'') def read(self, num=None): data = self.f.read(num) self.sha1.update(data) return data def check_sha(self): stored = self.f.read(20) if stored != self.sha1.digest(): raise ChecksumMismatch(self.sha1.hexdigest(), sha_to_hex(stored)) def close(self): return self.f.close() def tell(self): return self.f.tell() class SHA1Writer(object): """Wrapper around a file-like object that remembers the SHA1 of its data.""" def __init__(self, f): self.f = f self.length = 0 self.sha1 = sha1(b'') def write(self, data): self.sha1.update(data) self.f.write(data) self.length += len(data) def write_sha(self): sha = self.sha1.digest() assert len(sha) == 20 self.f.write(sha) self.length += len(sha) return sha def close(self): sha = self.write_sha() self.f.close() return sha def offset(self): return self.length def tell(self): return self.f.tell() def pack_object_header(type_num, delta_base, size): """Create a pack object header for the given object info. :param type_num: Numeric type of the object. :param delta_base: Delta base offset or ref, or None for whole objects. :param size: Uncompressed object size. :return: A header for a packed object. """ header = [] c = (type_num << 4) | (size & 15) size >>= 4 while size: header.append(c | 0x80) c = size & 0x7f size >>= 7 header.append(c) if type_num == OFS_DELTA: ret = [delta_base & 0x7f] delta_base >>= 7 while delta_base: delta_base -= 1 ret.insert(0, 0x80 | (delta_base & 0x7f)) delta_base >>= 7 header.extend(ret) elif type_num == REF_DELTA: assert len(delta_base) == 20 header += delta_base return bytearray(header) def write_pack_object(f, type, object, sha=None): """Write pack object to a file. :param f: File to write to :param type: Numeric type of the object :param object: Object to write :return: Tuple with offset at which the object was written, and crc32 """ if type in DELTA_TYPES: delta_base, object = object else: delta_base = None header = bytes(pack_object_header(type, delta_base, len(object))) comp_data = zlib.compress(object) crc32 = 0 for data in (header, comp_data): f.write(data) if sha is not None: sha.update(data) crc32 = binascii.crc32(data, crc32) return crc32 & 0xffffffff def write_pack(filename, objects, deltify=None, delta_window_size=None): """Write a new pack data file. :param filename: Path to the new pack file (without .pack extension) :param objects: Iterable of (object, path) tuples to write. Should provide __len__ :param window_size: Delta window size :param deltify: Whether to deltify pack objects :return: Tuple with checksum of pack file and index file """ with GitFile(filename + '.pack', 'wb') as f: entries, data_sum = write_pack_objects(f, objects, delta_window_size=delta_window_size, deltify=deltify) - entries = [(k, v[0], v[1]) for (k, v) in entries.items()] - entries.sort() + entries = sorted([(k, v[0], v[1]) for (k, v) in entries.items()]) with GitFile(filename + '.idx', 'wb') as f: return data_sum, write_pack_index_v2(f, entries, data_sum) def write_pack_header(f, num_objects): """Write a pack header for the given number of objects.""" f.write(b'PACK') # Pack header f.write(struct.pack(b'>L', 2)) # Pack version f.write(struct.pack(b'>L', num_objects)) # Number of objects in pack def deltify_pack_objects(objects, window_size=None): """Generate deltas for pack objects. :param objects: An iterable of (object, path) tuples to deltify. :param window_size: Window size; None for default :return: Iterator over type_num, object id, delta_base, content delta_base is None for full text entries """ if window_size is None: window_size = DEFAULT_PACK_DELTA_WINDOW_SIZE # Build a list of objects ordered by the magic Linus heuristic # This helps us find good objects to diff against us magic = [] for obj, path in objects: magic.append((obj.type_num, path, -obj.raw_length(), obj)) magic.sort() possible_bases = deque() for type_num, path, neg_length, o in magic: raw = o.as_raw_string() winner = raw winner_base = None for base in possible_bases: if base.type_num != type_num: continue delta = create_delta(base.as_raw_string(), raw) if len(delta) < len(winner): winner_base = base.sha().digest() winner = delta yield type_num, o.sha().digest(), winner_base, winner possible_bases.appendleft(o) while len(possible_bases) > window_size: possible_bases.pop() def write_pack_objects(f, objects, delta_window_size=None, deltify=False): """Write a new pack data file. :param f: File to write to :param objects: Iterable of (object, path) tuples to write. Should provide __len__ :param window_size: Sliding window size for searching for deltas; Set to None for default window size. :param deltify: Whether to deltify objects :return: Dict mapping id -> (offset, crc32 checksum), pack checksum """ if deltify: pack_contents = deltify_pack_objects(objects, delta_window_size) else: pack_contents = ( (o.type_num, o.sha().digest(), None, o.as_raw_string()) for (o, path) in objects) return write_pack_data(f, len(objects), pack_contents) def write_pack_data(f, num_records, records): """Write a new pack data file. :param f: File to write to :param num_records: Number of records :param records: Iterator over type_num, object_id, delta_base, raw :return: Dict mapping id -> (offset, crc32 checksum), pack checksum """ # Write the pack entries = {} f = SHA1Writer(f) write_pack_header(f, num_records) for type_num, object_id, delta_base, raw in records: offset = f.offset() if delta_base is not None: try: base_offset, base_crc32 = entries[delta_base] except KeyError: type_num = REF_DELTA raw = (delta_base, raw) else: type_num = OFS_DELTA raw = (offset - base_offset, raw) crc32 = write_pack_object(f, type_num, raw) entries[object_id] = (offset, crc32) return entries, f.write_sha() def write_pack_index_v1(f, entries, pack_checksum): """Write a new pack index file. :param f: A file-like object to write to :param entries: List of tuples with object name (sha), offset_in_pack, and crc32_checksum. :param pack_checksum: Checksum of the pack file. :return: The SHA of the written index file """ f = SHA1Writer(f) fan_out_table = defaultdict(lambda: 0) for (name, offset, entry_checksum) in entries: fan_out_table[ord(name[:1])] += 1 # Fan-out table for i in range(0x100): f.write(struct.pack('>L', fan_out_table[i])) fan_out_table[i+1] += fan_out_table[i] for (name, offset, entry_checksum) in entries: if not (offset <= 0xffffffff): raise TypeError("pack format 1 only supports offsets < 2Gb") f.write(struct.pack('>L20s', offset, name)) assert len(pack_checksum) == 20 f.write(pack_checksum) return f.write_sha() def _delta_encode_size(size): ret = bytearray() c = size & 0x7f size >>= 7 while size: ret.append(c | 0x80) c = size & 0x7f size >>= 7 ret.append(c) return ret # The length of delta compression copy operations in version 2 packs is limited # to 64K. To copy more, we use several copy operations. Version 3 packs allow # 24-bit lengths in copy operations, but we always make version 2 packs. _MAX_COPY_LEN = 0xffff def _encode_copy_operation(start, length): scratch = [] op = 0x80 for i in range(4): if start & 0xff << i*8: scratch.append((start >> i*8) & 0xff) op |= 1 << i for i in range(2): if length & 0xff << i*8: scratch.append((length >> i*8) & 0xff) op |= 1 << (4+i) return bytearray([op] + scratch) def create_delta(base_buf, target_buf): """Use python difflib to work out how to transform base_buf to target_buf. :param base_buf: Base buffer :param target_buf: Target buffer """ assert isinstance(base_buf, bytes) assert isinstance(target_buf, bytes) out_buf = bytearray() # write delta header out_buf += _delta_encode_size(len(base_buf)) out_buf += _delta_encode_size(len(target_buf)) # write out delta opcodes seq = difflib.SequenceMatcher(a=base_buf, b=target_buf) for opcode, i1, i2, j1, j2 in seq.get_opcodes(): # Git patch opcodes don't care about deletes! #if opcode == 'replace' or opcode == 'delete': # pass if opcode == 'equal': # If they are equal, unpacker will use data from base_buf # Write out an opcode that says what range to use copy_start = i1 copy_len = i2 - i1 while copy_len > 0: to_copy = min(copy_len, _MAX_COPY_LEN) out_buf += _encode_copy_operation(copy_start, to_copy) copy_start += to_copy copy_len -= to_copy if opcode == 'replace' or opcode == 'insert': # If we are replacing a range or adding one, then we just # output it to the stream (prefixed by its size) s = j2 - j1 o = j1 while s > 127: out_buf.append(127) out_buf += bytearray(target_buf[o:o+127]) s -= 127 o += 127 out_buf.append(s) out_buf += bytearray(target_buf[o:o+s]) return bytes(out_buf) def apply_delta(src_buf, delta): """Based on the similar function in git's patch-delta.c. :param src_buf: Source buffer :param delta: Delta instructions """ if not isinstance(src_buf, bytes): src_buf = b''.join(src_buf) if not isinstance(delta, bytes): delta = b''.join(delta) out = [] index = 0 delta_length = len(delta) def get_delta_header_size(delta, index): size = 0 i = 0 while delta: cmd = ord(delta[index:index+1]) index += 1 size |= (cmd & ~0x80) << i i += 7 if not cmd & 0x80: break return size, index src_size, index = get_delta_header_size(delta, index) dest_size, index = get_delta_header_size(delta, index) assert src_size == len(src_buf), '%d vs %d' % (src_size, len(src_buf)) while index < delta_length: cmd = ord(delta[index:index+1]) index += 1 if cmd & 0x80: cp_off = 0 for i in range(4): if cmd & (1 << i): x = ord(delta[index:index+1]) index += 1 cp_off |= x << (i * 8) cp_size = 0 # Version 3 packs can contain copy sizes larger than 64K. for i in range(3): if cmd & (1 << (4+i)): x = ord(delta[index:index+1]) index += 1 cp_size |= x << (i * 8) if cp_size == 0: cp_size = 0x10000 if (cp_off + cp_size < cp_size or cp_off + cp_size > src_size or cp_size > dest_size): break out.append(src_buf[cp_off:cp_off+cp_size]) elif cmd != 0: out.append(delta[index:index+cmd]) index += cmd else: raise ApplyDeltaError('Invalid opcode 0') if index != delta_length: raise ApplyDeltaError('delta not empty: %r' % delta[index:]) if dest_size != chunks_length(out): raise ApplyDeltaError('dest size incorrect') return out def write_pack_index_v2(f, entries, pack_checksum): """Write a new pack index file. :param f: File-like object to write to :param entries: List of tuples with object name (sha), offset_in_pack, and crc32_checksum. :param pack_checksum: Checksum of the pack file. :return: The SHA of the index file written """ f = SHA1Writer(f) f.write(b'\377tOc') # Magic! f.write(struct.pack('>L', 2)) fan_out_table = defaultdict(lambda: 0) for (name, offset, entry_checksum) in entries: fan_out_table[ord(name[:1])] += 1 # Fan-out table largetable = [] for i in range(0x100): f.write(struct.pack(b'>L', fan_out_table[i])) fan_out_table[i+1] += fan_out_table[i] for (name, offset, entry_checksum) in entries: f.write(name) for (name, offset, entry_checksum) in entries: f.write(struct.pack(b'>L', entry_checksum)) for (name, offset, entry_checksum) in entries: if offset < 2**31: f.write(struct.pack(b'>L', offset)) else: f.write(struct.pack(b'>L', 2**31 + len(largetable))) largetable.append(offset) for offset in largetable: f.write(struct.pack(b'>Q', offset)) assert len(pack_checksum) == 20 f.write(pack_checksum) return f.write_sha() write_pack_index = write_pack_index_v2 class Pack(object): """A Git pack object.""" def __init__(self, basename, resolve_ext_ref=None): self._basename = basename self._data = None self._idx = None self._idx_path = self._basename + '.idx' self._data_path = self._basename + '.pack' self._data_load = lambda: PackData(self._data_path) self._idx_load = lambda: load_pack_index(self._idx_path) self.resolve_ext_ref = resolve_ext_ref @classmethod def from_lazy_objects(self, data_fn, idx_fn): """Create a new pack object from callables to load pack data and index objects.""" ret = Pack('') ret._data_load = data_fn ret._idx_load = idx_fn return ret @classmethod def from_objects(self, data, idx): """Create a new pack object from pack data and index objects.""" ret = Pack('') ret._data_load = lambda: data ret._idx_load = lambda: idx return ret def name(self): """The SHA over the SHAs of the objects in this pack.""" return self.index.objects_sha1() @property def data(self): """The pack data object being used.""" if self._data is None: self._data = self._data_load() self._data.pack = self self.check_length_and_checksum() return self._data @property def index(self): """The index being used. :note: This may be an in-memory index """ if self._idx is None: self._idx = self._idx_load() return self._idx def close(self): if self._data is not None: self._data.close() if self._idx is not None: self._idx.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def __eq__(self, other): return isinstance(self, type(other)) and self.index == other.index def __len__(self): """Number of entries in this pack.""" return len(self.index) def __repr__(self): return '%s(%r)' % (self.__class__.__name__, self._basename) def __iter__(self): """Iterate over all the sha1s of the objects in this pack.""" return iter(self.index) def check_length_and_checksum(self): """Sanity check the length and checksum of the pack index and data.""" assert len(self.index) == len(self.data) idx_stored_checksum = self.index.get_pack_checksum() data_stored_checksum = self.data.get_stored_checksum() if idx_stored_checksum != data_stored_checksum: raise ChecksumMismatch(sha_to_hex(idx_stored_checksum), sha_to_hex(data_stored_checksum)) def check(self): """Check the integrity of this pack. :raise ChecksumMismatch: if a checksum for the index or data is wrong """ self.index.check() self.data.check() for obj in self.iterobjects(): obj.check() # TODO: object connectivity checks def get_stored_checksum(self): return self.data.get_stored_checksum() def __contains__(self, sha1): """Check whether this pack contains a particular SHA1.""" try: self.index.object_index(sha1) return True except KeyError: return False def get_raw(self, sha1): offset = self.index.object_index(sha1) obj_type, obj = self.data.get_object_at(offset) type_num, chunks = self.data.resolve_object(offset, obj_type, obj) return type_num, b''.join(chunks) def __getitem__(self, sha1): """Retrieve the specified SHA1.""" type, uncomp = self.get_raw(sha1) return ShaFile.from_raw_string(type, uncomp, sha=sha1) def iterobjects(self): """Iterate over the objects in this pack.""" return iter(PackInflater.for_pack_data( self.data, resolve_ext_ref=self.resolve_ext_ref)) def pack_tuples(self): """Provide an iterable for use with write_pack_objects. :return: Object that can iterate over (object, path) tuples and provides __len__ """ class PackTupleIterable(object): def __init__(self, pack): self.pack = pack def __len__(self): return len(self.pack) def __iter__(self): return ((o, None) for o in self.pack.iterobjects()) return PackTupleIterable(self) def keep(self, msg=None): """Add a .keep file for the pack, preventing git from garbage collecting it. :param msg: A message written inside the .keep file; can be used later to determine whether or not a .keep file is obsolete. :return: The path of the .keep file, as a string. """ keepfile_name = '%s.keep' % self._basename with GitFile(keepfile_name, 'wb') as keepfile: if msg: keepfile.write(msg) keepfile.write(b'\n') return keepfile_name try: from dulwich._pack import apply_delta, bisect_find_sha except ImportError: pass diff --git a/dulwich/patch.py b/dulwich/patch.py index 32f4df05..3c3158e9 100644 --- a/dulwich/patch.py +++ b/dulwich/patch.py @@ -1,311 +1,311 @@ # patch.py -- For dealing with packed-style patches. # Copyright (C) 2009-2013 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. # """Classes for dealing with git am-style patches. These patches are basically unified diffs with some extra metadata tacked on. """ from difflib import SequenceMatcher import email.parser import time from dulwich.objects import ( Blob, Commit, S_ISGITLINK, ) FIRST_FEW_BYTES = 8000 def write_commit_patch(f, commit, contents, progress, version=None, encoding=None): """Write a individual file patch. :param commit: Commit object :param progress: Tuple with current patch number and total. :return: tuple with filename and contents """ encoding = encoding or getattr(f, "encoding", "ascii") - if type(contents) is str: + if isinstance(contents, str): contents = contents.encode(encoding) (num, total) = progress f.write(b"From " + commit.id + b" " + time.ctime(commit.commit_time).encode(encoding) + b"\n") f.write(b"From: " + commit.author + b"\n") f.write(b"Date: " + time.strftime("%a, %d %b %Y %H:%M:%S %Z").encode(encoding) + b"\n") f.write(("Subject: [PATCH %d/%d] " % (num, total)).encode(encoding) + commit.message + b"\n") f.write(b"\n") f.write(b"---\n") try: import subprocess p = subprocess.Popen(["diffstat"], stdout=subprocess.PIPE, stdin=subprocess.PIPE) except (ImportError, OSError): pass # diffstat not available? else: (diffstat, _) = p.communicate(contents) f.write(diffstat) f.write(b"\n") f.write(contents) f.write(b"-- \n") if version is None: from dulwich import __version__ as dulwich_version f.write(b"Dulwich %d.%d.%d\n" % dulwich_version) else: f.write(version.encode(encoding) + b"\n") def get_summary(commit): """Determine the summary line for use in a filename. :param commit: Commit :return: Summary string """ return commit.message.splitlines()[0].replace(" ", "-") def unified_diff(a, b, fromfile, tofile, n=3): """difflib.unified_diff that doesn't write any dates or trailing spaces. Based on the same function in Python2.6.5-rc2's difflib.py """ started = False for group in SequenceMatcher(None, a, b).get_grouped_opcodes(n): if not started: yield b'--- ' + fromfile + b'\n' yield b'+++ ' + tofile + b'\n' started = True i1, i2, j1, j2 = group[0][1], group[-1][2], group[0][3], group[-1][4] sizes = "@@ -%d,%d +%d,%d @@\n" % (i1+1, i2-i1, j1+1, j2-j1) yield sizes.encode('ascii') for tag, i1, i2, j1, j2 in group: if tag == 'equal': for line in a[i1:i2]: yield b' ' + line continue if tag == 'replace' or tag == 'delete': for line in a[i1:i2]: if not line[-1:] == b'\n': line += b'\n\\ No newline at end of file\n' yield b'-' + line if tag == 'replace' or tag == 'insert': for line in b[j1:j2]: if not line[-1:] == b'\n': line += b'\n\\ No newline at end of file\n' yield b'+' + line def is_binary(content): """See if the first few bytes contain any null characters. :param content: Bytestring to check for binary content """ return b'\0' in content[:FIRST_FEW_BYTES] def shortid(hexsha): if hexsha is None: return b"0" * 7 else: return hexsha[:7] def patch_filename(p, root): if p is None: return b"/dev/null" else: return root + b"/" + p def write_object_diff(f, store, old_file, new_file, diff_binary=False): """Write the diff for an object. :param f: File-like object to write to :param store: Store to retrieve objects from, if necessary :param old_file: (path, mode, hexsha) tuple :param new_file: (path, mode, hexsha) tuple :param diff_binary: Whether to diff files even if they are considered binary files by is_binary(). :note: the tuple elements should be None for nonexistant files """ (old_path, old_mode, old_id) = old_file (new_path, new_mode, new_id) = new_file old_path = patch_filename(old_path, b"a") new_path = patch_filename(new_path, b"b") def content(mode, hexsha): if hexsha is None: return Blob.from_string(b'') elif S_ISGITLINK(mode): return Blob.from_string(b"Submodule commit " + hexsha + b"\n") else: return store[hexsha] def lines(content): if not content: return [] else: return content.splitlines() f.writelines(gen_diff_header( (old_path, new_path), (old_mode, new_mode), (old_id, new_id))) old_content = content(old_mode, old_id) new_content = content(new_mode, new_id) if not diff_binary and ( is_binary(old_content.data) or is_binary(new_content.data)): f.write(b"Binary files " + old_path + b" and " + new_path + b" differ\n") else: f.writelines(unified_diff(lines(old_content), lines(new_content), old_path, new_path)) # TODO(jelmer): Support writing unicode, rather than bytes. def gen_diff_header(paths, modes, shas): """Write a blob diff header. :param paths: Tuple with old and new path :param modes: Tuple with old and new modes :param shas: Tuple with old and new shas """ (old_path, new_path) = paths (old_mode, new_mode) = modes (old_sha, new_sha) = shas yield b"diff --git " + old_path + b" " + new_path + b"\n" if old_mode != new_mode: if new_mode is not None: if old_mode is not None: yield ("old mode %o\n" % old_mode).encode('ascii') yield ("new mode %o\n" % new_mode).encode('ascii') else: yield ("deleted mode %o\n" % old_mode).encode('ascii') yield b"index " + shortid(old_sha) + b".." + shortid(new_sha) if new_mode is not None: yield (" %o" % new_mode).encode('ascii') yield b"\n" # TODO(jelmer): Support writing unicode, rather than bytes. def write_blob_diff(f, old_file, new_file): """Write blob diff. :param f: File-like object to write to :param old_file: (path, mode, hexsha) tuple (None if nonexisting) :param new_file: (path, mode, hexsha) tuple (None if nonexisting) :note: The use of write_object_diff is recommended over this function. """ (old_path, old_mode, old_blob) = old_file (new_path, new_mode, new_blob) = new_file old_path = patch_filename(old_path, b"a") new_path = patch_filename(new_path, b"b") def lines(blob): if blob is not None: return blob.splitlines() else: return [] f.writelines(gen_diff_header( (old_path, new_path), (old_mode, new_mode), (getattr(old_blob, "id", None), getattr(new_blob, "id", None)))) old_contents = lines(old_blob) new_contents = lines(new_blob) f.writelines(unified_diff(old_contents, new_contents, old_path, new_path)) # TODO(jelmer): Support writing unicode, rather than bytes. def write_tree_diff(f, store, old_tree, new_tree, diff_binary=False): """Write tree diff. :param f: File-like object to write to. :param old_tree: Old tree id :param new_tree: New tree id :param diff_binary: Whether to diff files even if they are considered binary files by is_binary(). """ changes = store.tree_changes(old_tree, new_tree) for (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) in changes: write_object_diff(f, store, (oldpath, oldmode, oldsha), (newpath, newmode, newsha), diff_binary=diff_binary) def git_am_patch_split(f, encoding=None): """Parse a git-am-style patch and split it up into bits. :param f: File-like object to parse :param encoding: Encoding to use when creating Git objects :return: Tuple with commit object, diff contents and git version """ encoding = encoding or getattr(f, "encoding", "ascii") contents = f.read() - if type(contents) is bytes and getattr(email.parser, "BytesParser", None): + if isinstance(contents, bytes) and getattr(email.parser, "BytesParser", None): parser = email.parser.BytesParser() msg = parser.parsebytes(contents) else: parser = email.parser.Parser() msg = parser.parsestr(contents) return parse_patch_message(msg, encoding) def parse_patch_message(msg, encoding=None): """Extract a Commit object and patch from an e-mail message. :param msg: An email message (email.message.Message) :param encoding: Encoding to use to encode Git commits :return: Tuple with commit object, diff contents and git version """ c = Commit() c.author = msg["from"].encode(encoding) c.committer = msg["from"].encode(encoding) try: patch_tag_start = msg["subject"].index("[PATCH") except ValueError: subject = msg["subject"] else: close = msg["subject"].index("] ", patch_tag_start) subject = msg["subject"][close+2:] c.message = (subject.replace("\n", "") + "\n").encode(encoding) first = True body = msg.get_payload(decode=True) lines = body.splitlines(True) line_iter = iter(lines) for l in line_iter: if l == b"---\n": break if first: if l.startswith(b"From: "): c.author = l[len(b"From: "):].rstrip() else: c.message += b"\n" + l first = False else: c.message += l diff = b"" for l in line_iter: if l == b"-- \n": break diff += l try: version = next(line_iter).rstrip(b"\n") except StopIteration: version = None return c, diff, version diff --git a/dulwich/porcelain.py b/dulwich/porcelain.py index bcf23073..a9efcf26 100644 --- a/dulwich/porcelain.py +++ b/dulwich/porcelain.py @@ -1,981 +1,979 @@ # porcelain.py -- Porcelain-like layer on top of Dulwich # Copyright (C) 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. # """Simple wrapper that provides porcelain-like functions on top of Dulwich. Currently implemented: * archive * add * branch{_create,_delete,_list} * clone * commit * commit-tree * daemon * diff-tree * fetch * init * ls-remote * ls-tree * pull * push * rm * receive-pack * reset * rev-list * tag{_create,_delete,_list} * upload-pack * update-server-info * status * symbolic-ref These functions are meant to behave similarly to the git subcommands. Differences in behaviour are considered bugs. """ from collections import namedtuple from contextlib import ( closing, contextmanager, ) import os import posixpath import stat import sys import time from dulwich.archive import ( tar_stream, ) from dulwich.client import ( get_transport_and_path, ) from dulwich.diff_tree import ( CHANGE_ADD, CHANGE_DELETE, CHANGE_MODIFY, CHANGE_RENAME, CHANGE_COPY, RENAME_CHANGE_TYPES, ) from dulwich.errors import ( SendPackError, UpdateRefsError, ) from dulwich.index import get_unstaged_changes from dulwich.objects import ( Commit, Tag, format_timezone, parse_timezone, pretty_format_tree_entry, ) from dulwich.objectspec import ( parse_object, parse_reftuples, ) from dulwich.pack import ( write_pack_index, write_pack_objects, ) from dulwich.patch import write_tree_diff from dulwich.protocol import ( Protocol, ZERO_SHA, ) from dulwich.refs import ANNOTATED_TAG_SUFFIX from dulwich.repo import (BaseRepo, Repo) from dulwich.server import ( FileSystemBackend, TCPGitServer, ReceivePackHandler, UploadPackHandler, update_server_info as server_update_server_info, ) # Module level tuple definition for status output GitStatus = namedtuple('GitStatus', 'staged unstaged untracked') default_bytes_out_stream = getattr(sys.stdout, 'buffer', sys.stdout) default_bytes_err_stream = getattr(sys.stderr, 'buffer', sys.stderr) DEFAULT_ENCODING = 'utf-8' def open_repo(path_or_repo): """Open an argument that can be a repository or a path for a repository.""" if isinstance(path_or_repo, BaseRepo): return path_or_repo return Repo(path_or_repo) @contextmanager def _noop_context_manager(obj): """Context manager that has the same api as closing but does nothing.""" yield obj def open_repo_closing(path_or_repo): """Open an argument that can be a repository or a path for a repository. returns a context manager that will close the repo on exit if the argument is a path, else does nothing if the argument is a repo. """ if isinstance(path_or_repo, BaseRepo): return _noop_context_manager(path_or_repo) return closing(Repo(path_or_repo)) def archive(repo, committish=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream): """Create an archive. :param repo: Path of repository for which to generate an archive. :param committish: Commit SHA1 or ref to use :param outstream: Output stream (defaults to stdout) :param errstream: Error stream (defaults to stderr) """ if committish is None: committish = "HEAD" with open_repo_closing(repo) as repo_obj: c = repo_obj[committish] tree = c.tree for chunk in tar_stream(repo_obj.object_store, repo_obj.object_store[c.tree], c.commit_time): outstream.write(chunk) def update_server_info(repo="."): """Update server info files for a repository. :param repo: path to the repository """ with open_repo_closing(repo) as r: server_update_server_info(r) def symbolic_ref(repo, ref_name, force=False): """Set git symbolic ref into HEAD. :param repo: path to the repository :param ref_name: short name of the new ref :param force: force settings without checking if it exists in refs/heads """ with open_repo_closing(repo) as repo_obj: ref_path = b'refs/heads/' + ref_name if not force and ref_path not in repo_obj.refs.keys(): raise ValueError('fatal: ref `%s` is not a ref' % ref_name) repo_obj.refs.set_symbolic_ref(b'HEAD', ref_path) def commit(repo=".", message=None, author=None, committer=None): """Create a new commit. :param repo: Path to repository :param message: Optional commit message :param author: Optional author name and email :param committer: Optional committer name and email :return: SHA1 of the new commit """ # FIXME: Support --all argument # FIXME: Support --signoff argument with open_repo_closing(repo) as r: return r.do_commit(message=message, author=author, committer=committer) def commit_tree(repo, tree, message=None, author=None, committer=None): """Create a new commit object. :param repo: Path to repository :param tree: An existing tree object :param author: Optional author name and email :param committer: Optional committer name and email """ with open_repo_closing(repo) as r: return r.do_commit(message=message, tree=tree, committer=committer, author=author) def init(path=".", bare=False): """Create a new git repository. :param path: Path to repository. :param bare: Whether to create a bare repository. :return: A Repo instance """ if not os.path.exists(path): os.mkdir(path) if bare: return Repo.init_bare(path) else: return Repo.init(path) def clone(source, target=None, bare=False, checkout=None, errstream=default_bytes_err_stream, outstream=None, origin=b"origin"): """Clone a local or remote git repository. :param source: Path or URL for source repository :param target: Path to target repository (optional) :param bare: Whether or not to create a bare repository :param checkout: Whether or not to check-out HEAD after cloning :param errstream: Optional stream to write progress to :param outstream: Optional stream to write progress to (deprecated) :return: The new repository """ if outstream is not None: import warnings warnings.warn("outstream= has been deprecated in favour of errstream=.", DeprecationWarning, stacklevel=3) errstream = outstream if checkout is None: checkout = (not bare) if checkout and bare: raise ValueError("checkout and bare are incompatible") client, host_path = get_transport_and_path(source) if target is None: target = host_path.split("/")[-1] if not os.path.exists(target): os.mkdir(target) if bare: r = Repo.init_bare(target) else: r = Repo.init(target) try: remote_refs = client.fetch(host_path, r, determine_wants=r.object_store.determine_wants_all, progress=errstream.write) r.refs.import_refs( b'refs/remotes/' + origin, {n[len(b'refs/heads/'):]: v for (n, v) in remote_refs.items() if n.startswith(b'refs/heads/')}) r.refs.import_refs( b'refs/tags', {n[len(b'refs/tags/'):]: v for (n, v) in remote_refs.items() if n.startswith(b'refs/tags/') and not n.endswith(ANNOTATED_TAG_SUFFIX)}) r[b"HEAD"] = remote_refs[b"HEAD"] target_config = r.get_config() if not isinstance(source, bytes): source = source.encode(DEFAULT_ENCODING) target_config.set((b'remote', b'origin'), b'url', source) target_config.set((b'remote', b'origin'), b'fetch', b'+refs/heads/*:refs/remotes/origin/*') target_config.write_to_path() if checkout: errstream.write(b'Checking out HEAD\n') r.reset_index() except: r.close() raise return r def add(repo=".", paths=None): """Add files to the staging area. :param repo: Repository for the files :param paths: Paths to add. No value passed stages all modified files. """ with open_repo_closing(repo) as r: if not paths: # If nothing is specified, add all non-ignored files. paths = [] for dirpath, dirnames, filenames in os.walk(r.path): # Skip .git and below. if '.git' in dirnames: dirnames.remove('.git') for filename in filenames: paths.append(os.path.join(dirpath[len(r.path)+1:], filename)) # TODO(jelmer): Possibly allow passing in absolute paths? relpaths = [] if not isinstance(paths, list): paths = [paths] for p in paths: # FIXME: Support patterns, directories. if os.path.isabs(p) and p.startswith(repo.path): relpath = os.path.relpath(p, repo.path) else: relpath = p relpaths.append(relpath) r.stage(relpaths) def rm(repo=".", paths=None): """Remove files from the staging area. :param repo: Repository for the files :param paths: Paths to remove """ with open_repo_closing(repo) as r: index = r.open_index() for p in paths: del index[p.encode(sys.getfilesystemencoding())] index.write() def commit_decode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding is not None: return contents.decode(commit.encoding, "replace") return contents.decode(default_encoding, "replace") def print_commit(commit, decode, outstream=sys.stdout): """Write a human-readable commit log entry. :param commit: A `Commit` object :param outstream: A stream file to write to """ outstream.write("-" * 50 + "\n") outstream.write("commit: " + commit.id.decode('ascii') + "\n") if len(commit.parents) > 1: outstream.write("merge: " + "...".join([c.decode('ascii') for c in commit.parents[1:]]) + "\n") outstream.write("Author: " + decode(commit.author) + "\n") if commit.author != commit.committer: outstream.write("Committer: " + decode(commit.committer) + "\n") time_tuple = time.gmtime(commit.author_time + commit.author_timezone) time_str = time.strftime("%a %b %d %Y %H:%M:%S", time_tuple) timezone_str = format_timezone(commit.author_timezone).decode('ascii') outstream.write("Date: " + time_str + " " + timezone_str + "\n") outstream.write("\n") outstream.write(decode(commit.message) + "\n") outstream.write("\n") def print_tag(tag, decode, outstream=sys.stdout): """Write a human-readable tag. :param tag: A `Tag` object :param decode: Function for decoding bytes to unicode string :param outstream: A stream to write to """ outstream.write("Tagger: " + decode(tag.tagger) + "\n") outstream.write("Date: " + decode(tag.tag_time) + "\n") outstream.write("\n") outstream.write(decode(tag.message) + "\n") outstream.write("\n") def show_blob(repo, blob, decode, outstream=sys.stdout): """Write a blob to a stream. :param repo: A `Repo` object :param blob: A `Blob` object :param decode: Function for decoding bytes to unicode string :param outstream: A stream file to write to """ outstream.write(decode(blob.data)) def show_commit(repo, commit, decode, outstream=sys.stdout): """Show a commit to a stream. :param repo: A `Repo` object :param commit: A `Commit` object :param decode: Function for decoding bytes to unicode string :param outstream: Stream to write to """ print_commit(commit, decode=decode, outstream=outstream) parent_commit = repo[commit.parents[0]] write_tree_diff(outstream, repo.object_store, parent_commit.tree, commit.tree) def show_tree(repo, tree, decode, outstream=sys.stdout): """Print a tree to a stream. :param repo: A `Repo` object :param tree: A `Tree` object :param decode: Function for decoding bytes to unicode string :param outstream: Stream to write to """ for n in tree: outstream.write(decode(n) + "\n") def show_tag(repo, tag, decode, outstream=sys.stdout): """Print a tag to a stream. :param repo: A `Repo` object :param tag: A `Tag` object :param decode: Function for decoding bytes to unicode string :param outstream: Stream to write to """ print_tag(tag, decode, outstream) show_object(repo, repo[tag.object[1]], outstream) def show_object(repo, obj, decode, outstream): return { b"tree": show_tree, b"blob": show_blob, b"commit": show_commit, b"tag": show_tag, }[obj.type_name](repo, obj, decode, outstream) def print_name_status(changes): """Print a simple status summary, listing changed files. """ for change in changes: if not change: continue - if type(change) is list: + if isinstance(change, list): change = change[0] if change.type == CHANGE_ADD: path1 = change.new.path path2 = '' kind = 'A' elif change.type == CHANGE_DELETE: path1 = change.old.path path2 = '' kind = 'D' elif change.type == CHANGE_MODIFY: path1 = change.new.path path2 = '' kind = 'M' elif change.type in RENAME_CHANGE_TYPES: path1 = change.old.path path2 = change.new.path if change.type == CHANGE_RENAME: kind = 'R' elif change.type == CHANGE_COPY: kind = 'C' yield '%-8s%-20s%-20s' % (kind, path1, path2) def log(repo=".", paths=None, outstream=sys.stdout, max_entries=None, reverse=False, name_status=False): """Write commit logs. :param repo: Path to repository :param paths: Optional set of specific paths to print entries for :param outstream: Stream to write log output to :param reverse: Reverse order in which entries are printed :param name_status: Print name status :param max_entries: Optional maximum number of entries to display """ with open_repo_closing(repo) as r: walker = r.get_walker( max_entries=max_entries, paths=paths, reverse=reverse) for entry in walker: decode = lambda x: commit_decode(entry.commit, x) print_commit(entry.commit, decode, outstream) if name_status: outstream.writelines( [l+'\n' for l in print_name_status(entry.changes())]) # TODO(jelmer): better default for encoding? def show(repo=".", objects=None, outstream=sys.stdout, default_encoding=DEFAULT_ENCODING): """Print the changes in a commit. :param repo: Path to repository :param objects: Objects to show (defaults to [HEAD]) :param outstream: Stream to write to :param default_encoding: Default encoding to use if none is set in the commit """ if objects is None: objects = ["HEAD"] if not isinstance(objects, list): objects = [objects] with open_repo_closing(repo) as r: for objectish in objects: o = parse_object(r, objectish) if isinstance(o, Commit): decode = lambda x: commit_decode(o, x, default_encoding) else: decode = lambda x: x.decode(default_encoding) show_object(r, o, decode, outstream) def diff_tree(repo, old_tree, new_tree, outstream=sys.stdout): """Compares the content and mode of blobs found via two tree objects. :param repo: Path to repository :param old_tree: Id of old tree :param new_tree: Id of new tree :param outstream: Stream to write to """ with open_repo_closing(repo) as r: write_tree_diff(outstream, r.object_store, old_tree, new_tree) def rev_list(repo, commits, outstream=sys.stdout): """Lists commit objects in reverse chronological order. :param repo: Path to repository :param commits: Commits over which to iterate :param outstream: Stream to write to """ with open_repo_closing(repo) as r: for entry in r.get_walker(include=[r[c].id for c in commits]): outstream.write(entry.commit.id + b"\n") def tag(*args, **kwargs): import warnings warnings.warn("tag has been deprecated in favour of tag_create.", DeprecationWarning) return tag_create(*args, **kwargs) def tag_create(repo, tag, author=None, message=None, annotated=False, objectish="HEAD", tag_time=None, tag_timezone=None): """Creates a tag in git via dulwich calls: :param repo: Path to repository :param tag: tag string :param author: tag author (optional, if annotated is set) :param message: tag message (optional) :param annotated: whether to create an annotated tag :param objectish: object the tag should point at, defaults to HEAD :param tag_time: Optional time for annotated tag :param tag_timezone: Optional timezone for annotated tag """ with open_repo_closing(repo) as r: object = parse_object(r, objectish) if annotated: # Create the tag object tag_obj = Tag() if author is None: # TODO(jelmer): Don't use repo private method. author = r._get_user_identity() tag_obj.tagger = author tag_obj.message = message tag_obj.name = tag tag_obj.object = (type(object), object.id) if tag_time is None: tag_time = int(time.time()) tag_obj.tag_time = tag_time if tag_timezone is None: # TODO(jelmer) Use current user timezone rather than UTC tag_timezone = 0 elif isinstance(tag_timezone, str): tag_timezone = parse_timezone(tag_timezone) tag_obj.tag_timezone = tag_timezone r.object_store.add_object(tag_obj) tag_id = tag_obj.id else: tag_id = object.id r.refs[b'refs/tags/' + tag] = tag_id def list_tags(*args, **kwargs): import warnings warnings.warn("list_tags has been deprecated in favour of tag_list.", DeprecationWarning) return tag_list(*args, **kwargs) def tag_list(repo, outstream=sys.stdout): """List all tags. :param repo: Path to repository :param outstream: Stream to write tags to """ with open_repo_closing(repo) as r: - tags = list(r.refs.as_dict(b"refs/tags")) - tags.sort() + tags = sorted(r.refs.as_dict(b"refs/tags")) return tags def tag_delete(repo, name): """Remove a tag. :param repo: Path to repository :param name: Name of tag to remove """ with open_repo_closing(repo) as r: if isinstance(name, bytes): names = [name] elif isinstance(name, list): names = name else: raise TypeError("Unexpected tag name type %r" % name) for name in names: del r.refs[b"refs/tags/" + name] def reset(repo, mode, committish="HEAD"): """Reset current HEAD to the specified state. :param repo: Path to repository :param mode: Mode ("hard", "soft", "mixed") """ if mode != "hard": raise ValueError("hard is the only mode currently supported") with open_repo_closing(repo) as r: tree = r[committish].tree r.reset_index(tree) def push(repo, remote_location, refspecs=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream): """Remote push with dulwich via dulwich.client :param repo: Path to repository :param remote_location: Location of the remote :param refspecs: relative path to the refs to push to remote :param outstream: A stream file to write output :param errstream: A stream file to write errors """ # Open the repo with open_repo_closing(repo) as r: # Get the client and path client, path = get_transport_and_path(remote_location) selected_refs = [] def update_refs(refs): selected_refs.extend(parse_reftuples(r.refs, refs, refspecs)) new_refs = {} # TODO: Handle selected_refs == {None: None} for (lh, rh, force) in selected_refs: if lh is None: new_refs[rh] = ZERO_SHA else: new_refs[rh] = r.refs[lh] return new_refs err_encoding = getattr(errstream, 'encoding', None) or DEFAULT_ENCODING remote_location_bytes = client.get_url(path).encode(err_encoding) try: client.send_pack(path, update_refs, r.object_store.generate_pack_contents, progress=errstream.write) errstream.write(b"Push to " + remote_location_bytes + b" successful.\n") except (UpdateRefsError, SendPackError) as e: errstream.write(b"Push to " + remote_location_bytes + b" failed -> " + e.message.encode(err_encoding) + b"\n") def pull(repo, remote_location, refspecs=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream): """Pull from remote via dulwich.client :param repo: Path to repository :param remote_location: Location of the remote :param refspec: refspecs to fetch :param outstream: A stream file to write to output :param errstream: A stream file to write to errors """ # Open the repo with open_repo_closing(repo) as r: if refspecs is None: refspecs = [b"HEAD"] selected_refs = [] def determine_wants(remote_refs): selected_refs.extend(parse_reftuples(remote_refs, r.refs, refspecs)) return [remote_refs[lh] for (lh, rh, force) in selected_refs] client, path = get_transport_and_path(remote_location) remote_refs = client.fetch(path, r, progress=errstream.write, determine_wants=determine_wants) for (lh, rh, force) in selected_refs: r.refs[rh] = remote_refs[lh] if selected_refs: r[b'HEAD'] = remote_refs[selected_refs[0][1]] # Perform 'git checkout .' - syncs staged changes tree = r[b"HEAD"].tree r.reset_index() def status(repo="."): """Returns staged, unstaged, and untracked changes relative to the HEAD. :param repo: Path to repository or repository object :return: GitStatus tuple, staged - list of staged paths (diff index/HEAD) unstaged - list of unstaged paths (diff index/working-tree) untracked - list of untracked, un-ignored & non-.git paths """ with open_repo_closing(repo) as r: # 1. Get status of staged tracked_changes = get_tree_changes(r) # 2. Get status of unstaged unstaged_changes = list(get_unstaged_changes(r.open_index(), r.path)) # TODO - Status of untracked - add untracked changes, need gitignore. untracked_changes = [] return GitStatus(tracked_changes, unstaged_changes, untracked_changes) def get_tree_changes(repo): """Return add/delete/modify changes to tree by comparing index to HEAD. :param repo: repo path or object :return: dict with lists for each type of change """ with open_repo_closing(repo) as r: index = r.open_index() # Compares the Index to the HEAD & determines changes # Iterate through the changes and report add/delete/modify # TODO: call out to dulwich.diff_tree somehow. tracked_changes = { 'add': [], 'delete': [], 'modify': [], } try: tree_id = r[b'HEAD'].tree except KeyError: tree_id = None for change in index.changes_from_tree(r.object_store, tree_id): if not change[0][0]: tracked_changes['add'].append(change[0][1]) elif not change[0][1]: tracked_changes['delete'].append(change[0][0]) elif change[0][0] == change[0][1]: tracked_changes['modify'].append(change[0][0]) else: raise AssertionError('git mv ops not yet supported') return tracked_changes def daemon(path=".", address=None, port=None): """Run a daemon serving Git requests over TCP/IP. :param path: Path to the directory to serve. :param address: Optional address to listen on (defaults to ::) :param port: Optional port to listen on (defaults to TCP_GIT_PORT) """ # TODO(jelmer): Support git-daemon-export-ok and --export-all. backend = FileSystemBackend(path) server = TCPGitServer(backend, address, port) server.serve_forever() def web_daemon(path=".", address=None, port=None): """Run a daemon serving Git requests over HTTP. :param path: Path to the directory to serve :param address: Optional address to listen on (defaults to ::) :param port: Optional port to listen on (defaults to 80) """ from dulwich.web import ( make_wsgi_chain, make_server, WSGIRequestHandlerLogger, WSGIServerLogger) backend = FileSystemBackend(path) app = make_wsgi_chain(backend) server = make_server(address, port, app, handler_class=WSGIRequestHandlerLogger, server_class=WSGIServerLogger) server.serve_forever() def upload_pack(path=".", inf=None, outf=None): """Upload a pack file after negotiating its contents using smart protocol. :param path: Path to the repository :param inf: Input stream to communicate with client :param outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, 'buffer', sys.stdout) if inf is None: inf = getattr(sys.stdin, 'buffer', sys.stdin) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = UploadPackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def receive_pack(path=".", inf=None, outf=None): """Receive a pack file after negotiating its contents using smart protocol. :param path: Path to the repository :param inf: Input stream to communicate with client :param outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, 'buffer', sys.stdout) if inf is None: inf = getattr(sys.stdin, 'buffer', sys.stdin) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = ReceivePackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def branch_delete(repo, name): """Delete a branch. :param repo: Path to the repository :param name: Name of the branch """ with open_repo_closing(repo) as r: if isinstance(name, bytes): names = [name] elif isinstance(name, list): names = name else: raise TypeError("Unexpected branch name type %r" % name) for name in names: del r.refs[b"refs/heads/" + name] def branch_create(repo, name, objectish=None, force=False): """Create a branch. :param repo: Path to the repository :param name: Name of the new branch :param objectish: Target object to point new branch at (defaults to HEAD) :param force: Force creation of branch, even if it already exists """ with open_repo_closing(repo) as r: if isinstance(name, bytes): names = [name] elif isinstance(name, list): names = name else: raise TypeError("Unexpected branch name type %r" % name) if objectish is None: objectish = "HEAD" object = parse_object(r, objectish) refname = b"refs/heads/" + name if refname in r.refs and not force: raise KeyError("Branch with name %s already exists." % name) r.refs[refname] = object.id def branch_list(repo): """List all branches. :param repo: Path to the repository """ with open_repo_closing(repo) as r: return r.refs.keys(base=b"refs/heads/") def fetch(repo, remote_location, outstream=sys.stdout, errstream=default_bytes_err_stream): """Fetch objects from a remote server. :param repo: Path to the repository :param remote_location: String identifying a remote server :param outstream: Output stream (defaults to stdout) :param errstream: Error stream (defaults to stderr) :return: Dictionary with refs on the remote """ with open_repo_closing(repo) as r: client, path = get_transport_and_path(remote_location) remote_refs = client.fetch(path, r, progress=errstream.write) return remote_refs def ls_remote(remote): """List the refs in a remote. :param remote: Remote repository location :return: Dictionary with remote refs """ client, host_path = get_transport_and_path(remote) return client.get_refs(host_path) def repack(repo): """Repack loose files in a repository. Currently this only packs loose objects. :param repo: Path to the repository """ with open_repo_closing(repo) as r: r.object_store.pack_loose_objects() def pack_objects(repo, object_ids, packf, idxf, delta_window_size=None): """Pack objects into a file. :param repo: Path to the repository :param object_ids: List of object ids to write :param packf: File-like object to write to :param idxf: File-like object to write to (can be None) """ with open_repo_closing(repo) as r: entries, data_sum = write_pack_objects( packf, r.object_store.iter_shas((oid, None) for oid in object_ids), delta_window_size=delta_window_size) if idxf is not None: - entries = [(k, v[0], v[1]) for (k, v) in entries.items()] - entries.sort() + entries = sorted([(k, v[0], v[1]) for (k, v) in entries.items()]) write_pack_index(idxf, entries, data_sum) def ls_tree(repo, tree_ish=None, outstream=sys.stdout, recursive=False, name_only=False): """List contents of a tree. :param repo: Path to the repository :param tree_ish: Tree id to list :param outstream: Output stream (defaults to stdout) :param recursive: Whether to recursively list files :param name_only: Only print item name """ def list_tree(store, treeid, base): for (name, mode, sha) in store[treeid].iteritems(): if base: name = posixpath.join(base, name) if name_only: outstream.write(name + b"\n") else: outstream.write(pretty_format_tree_entry(name, mode, sha)) if stat.S_ISDIR(mode): list_tree(store, sha, name) if tree_ish is None: tree_ish = "HEAD" with open_repo_closing(repo) as r: c = r[tree_ish] treeid = c.tree list_tree(r.object_store, treeid, "")