diff --git a/dulwich/client.py b/dulwich/client.py index 9cd0e958..42726ef6 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1896 +1,1896 @@ # 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 * shallow Known capabilities that are not supported: * no-progress * include-tag """ from contextlib import closing from io import BytesIO, BufferedReader import errno import os import select import socket import subprocess import sys from urllib.parse import ( quote as urlquote, unquote as urlunquote, urlparse, urljoin, urlunparse, urlunsplit, urlunparse, ) import dulwich from dulwich.config import get_xdg_config_home_path from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, UpdateRefsError, ) from dulwich.protocol import ( HangupException, _RBUFSIZE, agent_string, capability_agent, extract_capability_names, CAPABILITY_AGENT, CAPABILITY_DELETE_REFS, CAPABILITY_INCLUDE_TAG, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, CAPABILITY_SHALLOW, CAPABILITY_SYMREF, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITIES_REF, KNOWN_RECEIVE_CAPABILITIES, KNOWN_UPLOAD_CAPABILITIES, COMMAND_DEEPEN, COMMAND_SHALLOW, COMMAND_UNSHALLOW, COMMAND_DONE, COMMAND_HAVE, COMMAND_WANT, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, PktLineParser, Protocol, ProtocolFile, TCP_GIT_PORT, ZERO_SHA, extract_capabilities, parse_capability, ) from dulwich.pack import ( write_pack_data, write_pack_objects, ) from dulwich.refs import ( read_info_refs, ANNOTATED_TAG_SUFFIX, ) class InvalidWants(Exception): """Invalid wants.""" def __init__(self, wants): Exception.__init__( self, "requested wants not in server provided refs: %r" % wants) def _fileno_can_read(fileno): """Check if a file descriptor is readable. """ return len(select.select([fileno], [], [], 0)[0]) > 0 def _win32_peek_avail(handle): """Wrapper around PeekNamedPipe to check how many bytes are available. """ from ctypes import byref, wintypes, windll c_avail = wintypes.DWORD() c_message = wintypes.DWORD() success = windll.kernel32.PeekNamedPipe( handle, None, 0, None, byref(c_avail), byref(c_message)) if not success: raise OSError(wintypes.GetLastError()) return c_avail.value COMMON_CAPABILITIES = [CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K] UPLOAD_CAPABILITIES = ([CAPABILITY_THIN_PACK, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_SHALLOW] + COMMON_CAPABILITIES) RECEIVE_CAPABILITIES = ( [CAPABILITY_REPORT_STATUS, CAPABILITY_DELETE_REFS] + 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. Raises: SendPackError: Raised when the server could not unpack UpdateRefsError: Raised when refs could not be updated """ if self._pack_status not in (b'unpack ok', None): raise SendPackError(self._pack_status) if not self._ref_status_ok: ref_status = {} ok = set() for status in self._ref_statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status # TODO(jelmer): don't assume encoding of refs is ascii. raise UpdateRefsError(', '.join([ refname.decode('ascii') for refname in ref_status if refname not in ok]) + ' failed to update', ref_status=ref_status) def handle_packet(self, pkt): """Handle a packet. Raises: GitProtocolError: Raised when packets are received after a flush packet. """ if self._done: raise GitProtocolError("received more data after status report") if pkt is None: self._done = True return if self._pack_status is None: self._pack_status = pkt.strip() else: ref_status = pkt.strip() self._ref_statuses.append(ref_status) if not ref_status.startswith(b'ok '): self._ref_status_ok = False def read_pkt_refs(proto): server_capabilities = None refs = {} # Receive refs from server for pkt in proto.read_pkt_seq(): (sha, ref) = pkt.rstrip(b'\n').split(None, 1) if sha == b'ERR': raise GitProtocolError(ref.decode('utf-8', 'replace')) if server_capabilities is None: (ref, server_capabilities) = extract_capabilities(ref) refs[ref] = sha if len(refs) == 0: return {}, set([]) if refs == {CAPABILITIES_REF: ZERO_SHA}: refs = {} return refs, set(server_capabilities) class FetchPackResult(object): """Result of a fetch-pack operation. Attributes: refs: Dictionary with all remote refs symrefs: Dictionary with remote symrefs agent: User agent string """ _FORWARDED_ATTRS = [ 'clear', 'copy', 'fromkeys', 'get', 'has_key', 'items', 'iteritems', 'iterkeys', 'itervalues', 'keys', 'pop', 'popitem', 'setdefault', 'update', 'values', 'viewitems', 'viewkeys', 'viewvalues'] def __init__(self, refs, symrefs, agent, new_shallow=None, new_unshallow=None): self.refs = refs self.symrefs = symrefs self.agent = agent self.new_shallow = new_shallow self.new_unshallow = new_unshallow def _warn_deprecated(self): import warnings warnings.warn( "Use FetchPackResult.refs instead.", DeprecationWarning, stacklevel=3) def __eq__(self, other): if isinstance(other, dict): self._warn_deprecated() return (self.refs == other) return (self.refs == other.refs and self.symrefs == other.symrefs and self.agent == other.agent) def __contains__(self, name): self._warn_deprecated() return name in self.refs def __getitem__(self, name): self._warn_deprecated() return self.refs[name] def __len__(self): self._warn_deprecated() return len(self.refs) def __iter__(self): self._warn_deprecated() return iter(self.refs) def __getattribute__(self, name): if name in type(self)._FORWARDED_ATTRS: self._warn_deprecated() return getattr(self.refs, name) return super(FetchPackResult, self).__getattribute__(name) def __repr__(self): return "%s(%r, %r, %r)" % ( self.__class__.__name__, self.refs, self.symrefs, self.agent) def _read_shallow_updates(proto): new_shallow = set() new_unshallow = set() for pkt in proto.read_pkt_seq(): cmd, sha = pkt.split(b' ', 1) if cmd == COMMAND_SHALLOW: new_shallow.add(sha.strip()) elif cmd == COMMAND_UNSHALLOW: new_unshallow.add(sha.strip()) else: raise GitProtocolError('unknown command %s' % pkt) return (new_shallow, new_unshallow) # 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, include_tags=False): """Create a new GitClient instance. Args: thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. include_tags: send annotated tags when sending the objects they point to """ self._report_activity = report_activity self._report_status_parser = None self._fetch_capabilities = set(UPLOAD_CAPABILITIES) self._fetch_capabilities.add(capability_agent()) self._send_capabilities = set(RECEIVE_CAPABILITIES) self._send_capabilities.add(capability_agent()) if quiet: self._send_capabilities.add(CAPABILITY_QUIET) if not thin_packs: self._fetch_capabilities.remove(CAPABILITY_THIN_PACK) if include_tags: self._fetch_capabilities.add(CAPABILITY_INCLUDE_TAG) def get_url(self, path): """Retrieves full url to given path. Args: path: Repository path (as string) Returns: 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. Args: parsedurl: Result of urlparse() Returns: A `GitClient` object """ raise NotImplementedError(cls.from_parsedurl) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) generate_pack_data: Function that can return a tuple with number of objects and list of pack data to include progress: Optional progress function Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data UpdateRefsError: if the server supports report-status and rejects ref updates """ raise NotImplementedError(self.send_pack) def fetch(self, path, target, determine_wants=None, progress=None, depth=None): """Fetch into a target repository. Args: path: Path to fetch from (as bytestring) target: Target repository to fetch into determine_wants: Optional function to determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. progress: Optional progress function depth: Depth to fetch at Returns: Dictionary with all remote refs (not just those fetched) """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all if CAPABILITY_THIN_PACK in self._fetch_capabilities: # TODO(jelmer): Avoid reading entire file into memory and # only processing it after the whole file has been fetched. f = BytesIO() def commit(): if f.tell(): f.seek(0) target.object_store.add_thin_pack(f.read, None) def abort(): pass else: f, commit, abort = target.object_store.add_pack() try: result = self.fetch_pack( path, determine_wants, target.get_graph_walker(), f.write, progress=progress, depth=depth) except BaseException: abort() raise else: commit() target.update_shallow(result.new_shallow, result.new_unshallow) return result def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Remote path to fetch from determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Shallow fetch depth Returns: FetchPackResult object """ raise NotImplementedError(self.fetch_pack) def get_refs(self, path): """Retrieve the current refs from a git smart server. Args: path: Path to the repo to fetch from. (as bytestring) Returns: """ raise NotImplementedError(self.get_refs) def _parse_status_report(self, proto): unpack = proto.read_pkt_line().strip() if unpack != b'unpack ok': st = True # flush remaining error data while st is not None: st = proto.read_pkt_line() raise SendPackError(unpack) statuses = [] errs = False ref_status = proto.read_pkt_line() while ref_status: ref_status = ref_status.strip() statuses.append(ref_status) if not ref_status.startswith(b'ok '): errs = True ref_status = proto.read_pkt_line() if errs: ref_status = {} ok = set() for status in statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status raise UpdateRefsError(', '.join([ refname for refname in ref_status if refname not in ok]) + b' failed to update', ref_status=ref_status) def _read_side_band64k_data(self, proto, channel_callbacks): """Read per-channel data. This requires the side-band-64k capability. Args: proto: Protocol object to read from 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. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities old_refs: Old refs, as received from the server new_refs: Refs to change Returns: 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(sorted(capabilities))) sent_capabilities = True if new_sha1 not in have and new_sha1 != ZERO_SHA: want.append(new_sha1) proto.write_pkt_line(None) return (have, want) def _negotiate_receive_pack_capabilities(self, server_capabilities): negotiated_capabilities = ( self._send_capabilities & server_capabilities) unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_RECEIVE_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities return negotiated_capabilities def _handle_receive_pack_tail(self, proto, capabilities, progress=None): """Handle the tail of a 'git-receive-pack' request. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities progress: Optional progress reporting function Returns: """ if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: def progress(x): pass channel_callbacks = {2: progress} if CAPABILITY_REPORT_STATUS in capabilities: channel_callbacks[1] = PktLineParser( self._report_status_parser.handle_packet).parse self._read_side_band64k_data(proto, channel_callbacks) else: if CAPABILITY_REPORT_STATUS in capabilities: for pkt in proto.read_pkt_seq(): self._report_status_parser.handle_packet(pkt) if self._report_status_parser is not None: self._report_status_parser.check() def _negotiate_upload_pack_capabilities(self, server_capabilities): unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_UPLOAD_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities symrefs = {} agent = None for capability in server_capabilities: k, v = parse_capability(capability) if k == CAPABILITY_SYMREF: (src, dst) = v.split(b':', 1) symrefs[src] = dst if k == CAPABILITY_AGENT: agent = v negotiated_capabilities = ( self._fetch_capabilities & server_capabilities) return (negotiated_capabilities, symrefs, agent) def _handle_upload_pack_head(self, proto, capabilities, graph_walker, wants, can_read, depth): """Handle the head of a 'git-upload-pack' request. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities graph_walker: GraphWalker instance to call .ack() on wants: List of commits to fetch can_read: function that returns a boolean that indicates whether there is extra graph data to read on proto depth: Depth for request Returns: """ assert isinstance(wants, list) and isinstance(wants[0], bytes) proto.write_pkt_line(COMMAND_WANT + b' ' + wants[0] + b' ' + b' '.join(sorted(capabilities)) + b'\n') for want in wants[1:]: proto.write_pkt_line(COMMAND_WANT + b' ' + want + b'\n') if depth not in (0, None) or getattr(graph_walker, 'shallow', None): if CAPABILITY_SHALLOW not in capabilities: raise GitProtocolError( "server does not support shallow capability required for " "depth") for sha in graph_walker.shallow: proto.write_pkt_line(COMMAND_SHALLOW + b' ' + sha + b'\n') if depth is not None: proto.write_pkt_line(COMMAND_DEEPEN + b' ' + str(depth).encode('ascii') + b'\n') proto.write_pkt_line(None) if can_read is not None: (new_shallow, new_unshallow) = _read_shallow_updates(proto) else: new_shallow = new_unshallow = None else: new_shallow = new_unshallow = set() proto.write_pkt_line(None) have = next(graph_walker) while have: proto.write_pkt_line(COMMAND_HAVE + b' ' + have + b'\n') if can_read is not None and 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') return (new_shallow, new_unshallow) 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. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities graph_walker: GraphWalker instance to call .ack() on pack_data: Function to call with pack data progress: Optional progress reporting function rbufsize: Read buffer size Returns: """ pkt = proto.read_pkt_line() while pkt: parts = pkt.rstrip(b'\n').split(b' ') if parts[0] == b'ACK': graph_walker.ack(parts[1]) if len(parts) < 3 or parts[2] not in ( b'ready', b'continue', b'common'): break pkt = proto.read_pkt_line() if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: # Just ignore progress data def progress(x): pass self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: pack_data, SIDE_BAND_CHANNEL_PROGRESS: progress} ) else: while True: data = proto.read(rbufsize) if data == b"": break pack_data(data) def check_wants(wants, refs): """Check that a set of wants is valid. Args: wants: Set of object SHAs to fetch refs: Refs dictionary to check against Returns: """ missing = set(wants) - { v for (k, v) in refs.items() if not k.endswith(ANNOTATED_TAG_SUFFIX)} if missing: raise InvalidWants(missing) def remote_error_from_stderr(stderr): if stderr is None: return HangupException() for l in stderr.readlines(): if l.startswith(b'ERROR: '): return GitProtocolError( l[len(b'ERROR: '):].decode('utf-8', 'replace')) return GitProtocolError(l.decode('utf-8', 'replace')) return HangupException() class TraditionalGitClient(GitClient): """Traditional Git client.""" DEFAULT_ENCODING = 'utf-8' def __init__(self, path_encoding=DEFAULT_ENCODING, **kwargs): self._remote_path_encoding = path_encoding super(TraditionalGitClient, self).__init__(**kwargs) def _connect(self, cmd, path): """Create a connection to the server. This method is abstract - concrete implementations should implement their own variant which connects to the server and returns an initialized Protocol object with the service ready for use and a can_read function which may be used to see if reads would block. Args: cmd: The git service name to which we should connect. path: The path we should pass to the service. (as bytestirng) """ raise NotImplementedError() def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) generate_pack_data: Function that can return a tuple with number of objects and pack data to upload. progress: Optional callback called with progress updates Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data UpdateRefsError: if the server supports report-status and rejects ref updates """ proto, unused_can_read, stderr = self._connect(b'receive-pack', path) with proto: try: old_refs, server_capabilities = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) negotiated_capabilities = \ self._negotiate_receive_pack_capabilities(server_capabilities) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() report_status_parser = self._report_status_parser try: new_refs = orig_new_refs = update_refs(dict(old_refs)) except BaseException: proto.write_pkt_line(None) raise if CAPABILITY_DELETE_REFS not in server_capabilities: # Server does not support deletions. Fail later. new_refs = dict(orig_new_refs) for ref, sha in orig_new_refs.items(): if sha == ZERO_SHA: if CAPABILITY_REPORT_STATUS in negotiated_capabilities: report_status_parser._ref_statuses.append( b'ng ' + sha + b' remote does not support deleting refs') report_status_parser._ref_status_ok = False del new_refs[ref] if new_refs is None: proto.write_pkt_line(None) return old_refs if len(new_refs) == 0 and len(orig_new_refs): # NOOP - Original new refs filtered out by policy proto.write_pkt_line(None) if report_status_parser is not None: report_status_parser.check() return old_refs (have, want) = self._handle_receive_pack_head( proto, negotiated_capabilities, old_refs, new_refs) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) dowrite = bool(pack_data_count) dowrite = dowrite or any(old_refs.get(ref) != sha for (ref, sha) in new_refs.items() if sha != ZERO_SHA) if dowrite: write_pack_data(proto.write_file(), pack_data_count, pack_data) self._handle_receive_pack_tail( proto, negotiated_capabilities, progress) return new_refs def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Remote path to fetch from determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Shallow fetch depth Returns: FetchPackResult object """ proto, can_read, stderr = self._connect(b'upload-pack', path) with proto: try: refs, server_capabilities = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) if refs is None: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) try: wants = determine_wants(refs) except BaseException: proto.write_pkt_line(None) raise if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) (new_shallow, new_unshallow) = self._handle_upload_pack_head( proto, negotiated_capabilities, graph_walker, wants, can_read, depth=depth) self._handle_upload_pack_tail( proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult( refs, symrefs, agent, new_shallow, new_unshallow) def get_refs(self, path): """Retrieve the current refs from a git smart server. """ # stock `git ls-remote` uses upload-pack proto, _, stderr = self._connect(b'upload-pack', path) with proto: try: refs, _ = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) proto.write_pkt_line(None) return refs def archive(self, path, committish, write_data, progress=None, write_error=None, format=None, subdirs=None, prefix=None): proto, can_read, stderr = self._connect(b'upload-archive', path) with proto: if format is not None: proto.write_pkt_line(b"argument --format=" + format) proto.write_pkt_line(b"argument " + committish) if subdirs is not None: for subdir in subdirs: proto.write_pkt_line(b"argument " + subdir) if prefix is not None: proto.write_pkt_line(b"argument --prefix=" + prefix) proto.write_pkt_line(None) try: pkt = proto.read_pkt_line() except HangupException: raise remote_error_from_stderr(stderr) if pkt == b"NACK\n": return elif pkt == b"ACK\n": pass elif pkt.startswith(b"ERR "): raise GitProtocolError( pkt[4:].rstrip(b"\n").decode('utf-8', 'replace')) else: raise AssertionError("invalid response %r" % pkt) ret = proto.read_pkt_line() if ret is not None: raise AssertionError("expected pkt tail") self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: write_data, SIDE_BAND_CHANNEL_PROGRESS: progress, SIDE_BAND_CHANNEL_FATAL: write_error}) class TCPGitClient(TraditionalGitClient): """A Git Client that works over TCP directly (i.e. git://).""" def __init__(self, host, port=None, **kwargs): if port is None: port = TCP_GIT_PORT self._host = host self._port = port super(TCPGitClient, self).__init__(**kwargs) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(parsedurl.hostname, port=parsedurl.port, **kwargs) def get_url(self, path): netloc = self._host if self._port is not None and self._port != TCP_GIT_PORT: netloc += ":%d" % self._port return urlunsplit(("git", netloc, path, '', '')) def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if not isinstance(path, bytes): path = path.encode(self._remote_path_encoding) sockaddrs = socket.getaddrinfo( self._host, self._port, socket.AF_UNSPEC, socket.SOCK_STREAM) s = None err = socket.error("no address found for %s" % self._host) for (family, socktype, proto, canonname, sockaddr) in sockaddrs: s = socket.socket(family, socktype, proto) s.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1) try: s.connect(sockaddr) break except socket.error as e: err = e if s is not None: s.close() s = None if s is None: raise err # -1 means system default buffering rfile = s.makefile('rb', -1) # 0 means unbuffered wfile = s.makefile('wb', 0) def close(): rfile.close() wfile.close() s.close() proto = Protocol(rfile.read, wfile.write, close, report_activity=self._report_activity) if path.startswith(b"/~"): path = path[1:] # TODO(jelmer): Alternative to ascii? proto.send_cmd( b'git-' + cmd, path, b'host=' + self._host.encode('ascii')) return proto, lambda: _fileno_can_read(s), None class SubprocessWrapper(object): """A socket-like object that talks to a subprocess via pipes.""" def __init__(self, proc): self.proc = proc self.read = BufferedReader(proc.stdout).read self.write = proc.stdin.write @property def stderr(self): return self.proc.stderr def can_read(self): if sys.platform == 'win32': from msvcrt import get_osfhandle handle = get_osfhandle(self.proc.stdout.fileno()) return _win32_peek_avail(handle) != 0 else: return _fileno_can_read(self.proc.stdout.fileno()) def close(self): self.proc.stdin.close() self.proc.stdout.close() if self.proc.stderr: self.proc.stderr.close() self.proc.wait() def find_git_command(): """Find command to run for system Git (usually C Git).""" if sys.platform == 'win32': # support .exe, .bat and .cmd try: # to avoid overhead import win32api except ImportError: # run through cmd.exe with some overhead return ['cmd', '/c', 'git'] else: status, git = win32api.FindExecutable('git') return [git] else: return ['git'] class SubprocessGitClient(TraditionalGitClient): """Git client that talks to a server using a subprocess.""" @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) git_command = None def _connect(self, service, path): if not isinstance(service, bytes): raise TypeError(service) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if self.git_command is None: git_command = find_git_command() argv = git_command + [service.decode('ascii'), path] p = subprocess.Popen(argv, bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) pw = SubprocessWrapper(p) return (Protocol(pw.read, pw.write, pw.close, report_activity=self._report_activity), pw.can_read, p.stderr) class LocalGitClient(GitClient): """Git Client that just uses a local Repo.""" def __init__(self, thin_packs=True, report_activity=None, config=None): """Create a new LocalGitClient instance. Args: thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. """ self._report_activity = report_activity # Ignore the thin_packs argument def get_url(self, path): return 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()) + path = os.fsdecode(path) return closing(Repo(path)) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) with number of items and pack data to upload. progress: Optional progress function Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data UpdateRefsError: if the server supports report-status and rejects ref updates """ if not progress: def progress(x): pass with self._open_repo(path) as target: old_refs = target.get_refs() new_refs = update_refs(dict(old_refs)) have = [sha1 for sha1 in old_refs.values() if sha1 != ZERO_SHA] want = [] for refname, new_sha1 in new_refs.items(): if (new_sha1 not in have and new_sha1 not in want and new_sha1 != ZERO_SHA): want.append(new_sha1) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs target.object_store.add_pack_data( *generate_pack_data(have, want, ofs_delta=True)) for refname, new_sha1 in new_refs.items(): old_sha1 = old_refs.get(refname, ZERO_SHA) if new_sha1 != ZERO_SHA: if not target.refs.set_if_equals( refname, old_sha1, new_sha1): progress('unable to set %s to %s' % (refname, new_sha1)) else: if not target.refs.remove_if_equals(refname, old_sha1): progress('unable to remove %s' % refname) return new_refs def fetch(self, path, target, determine_wants=None, progress=None, depth=None): """Fetch into a target repository. Args: path: Path to fetch from (as bytestring) target: Target repository to fetch into determine_wants: Optional function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. progress: Optional progress function depth: Shallow fetch depth Returns: FetchPackResult object """ with self._open_repo(path) as r: refs = r.fetch(target, determine_wants=determine_wants, progress=progress, depth=depth) return FetchPackResult(refs, r.refs.get_symrefs(), agent_string()) def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Remote path to fetch from determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Shallow fetch depth Returns: FetchPackResult object """ with self._open_repo(path) as r: objects_iter = r.fetch_objects( determine_wants, graph_walker, progress=progress, depth=depth) symrefs = r.refs.get_symrefs() agent = agent_string() # Did the process short-circuit (e.g. in a stateless RPC call)? # Note that the client still expects a 0-object pack in most cases. if objects_iter is None: return FetchPackResult(None, symrefs, agent) protocol = ProtocolFile(None, pack_data) write_pack_objects(protocol, objects_iter) return FetchPackResult(r.get_refs(), symrefs, agent) def get_refs(self, path): """Retrieve the current refs from a git smart server. """ with self._open_repo(path) as target: return target.get_refs() # What Git client to use for local access default_local_git_client_cls = LocalGitClient class SSHVendor(object): """A client side SSH implementation.""" def connect_ssh(self, host, command, username=None, port=None, password=None, key_filename=None): # This function was deprecated in 0.9.1 import warnings warnings.warn( "SSHVendor.connect_ssh has been renamed to SSHVendor.run_command", DeprecationWarning) return self.run_command(host, command, username=username, port=port, password=password, key_filename=key_filename) def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): """Connect to an SSH server. Run a command remotely and return a file-like object for interaction with the remote command. Args: host: Host name command: Command to run (as argv array) username: Optional ame of user to log in as port: Optional SSH port to use password: Optional ssh password for login or private key key_filename: Optional path to private keyfile Returns: """ raise NotImplementedError(self.run_command) class StrangeHostname(Exception): """Refusing to connect to strange SSH hostname.""" def __init__(self, hostname): super(StrangeHostname, self).__init__(hostname) class SubprocessSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'ssh' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if password is not None: raise NotImplementedError( "Setting password not supported by SubprocessSSHVendor.") args = ['ssh', '-x'] if port: args.extend(['-p', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return SubprocessWrapper(proc) class PLinkSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'plink' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if sys.platform == 'win32': args = ['plink.exe', '-ssh'] else: args = ['plink', '-ssh'] if password is not None: import warnings warnings.warn( "Invoking PLink with a password exposes the password in the " "process list.") args.extend(['-pw', str(password)]) if port: args.extend(['-P', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return SubprocessWrapper(proc) def ParamikoSSHVendor(**kwargs): import warnings warnings.warn( "ParamikoSSHVendor has been moved to dulwich.contrib.paramiko_vendor.", DeprecationWarning) from dulwich.contrib.paramiko_vendor import ParamikoSSHVendor return ParamikoSSHVendor(**kwargs) # Can be overridden by users get_ssh_vendor = SubprocessSSHVendor class SSHGitClient(TraditionalGitClient): def __init__(self, host, port=None, username=None, vendor=None, config=None, password=None, key_filename=None, **kwargs): self.host = host self.port = port self.username = username self.password = password self.key_filename = key_filename super(SSHGitClient, self).__init__(**kwargs) self.alternative_paths = {} if vendor is not None: self.ssh_vendor = vendor else: self.ssh_vendor = get_ssh_vendor() def get_url(self, path): netloc = self.host if self.port is not None: netloc += ":%d" % self.port if self.username is not None: netloc = urlquote(self.username, '@/:') + "@" + netloc return urlunsplit(('ssh', netloc, path, '', '')) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(host=parsedurl.hostname, port=parsedurl.port, username=parsedurl.username, **kwargs) def _get_cmd_path(self, cmd): cmd = self.alternative_paths.get(cmd, b'git-' + cmd) assert isinstance(cmd, bytes) return cmd def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if path.startswith("/~"): path = path[1:] argv = (self._get_cmd_path(cmd).decode(self._remote_path_encoding) + " '" + path + "'") kwargs = {} if self.password is not None: kwargs['password'] = self.password if self.key_filename is not None: kwargs['key_filename'] = self.key_filename con = self.ssh_vendor.run_command( self.host, argv, port=self.port, username=self.username, **kwargs) return (Protocol(con.read, con.write, con.close, report_activity=self._report_activity), con.can_read, getattr(con, 'stderr', None)) def default_user_agent_string(): # Start user agent with "git/", because GitHub requires this. :-( See # https://github.com/jelmer/dulwich/issues/562 for details. return "git/dulwich/%s" % ".".join([str(x) for x in dulwich.__version__]) def default_urllib3_manager(config, pool_manager_cls=None, proxy_manager_cls=None, **override_kwargs): """Return `urllib3` connection pool manager. Honour detected proxy configurations. Args: config: dulwich.config.ConfigDict` instance with Git configuration. kwargs: Additional arguments for urllib3.ProxyManager Returns: `pool_manager_cls` (defaults to `urllib3.ProxyManager`) instance for proxy configurations, `proxy_manager_cls` (defaults to `urllib3.PoolManager`) instance otherwise. """ proxy_server = user_agent = None ca_certs = ssl_verify = None if config is not None: try: proxy_server = config.get(b"http", b"proxy") except KeyError: pass try: user_agent = config.get(b"http", b"useragent") except KeyError: pass # TODO(jelmer): Support per-host settings try: ssl_verify = config.get_boolean(b"http", b"sslVerify") except KeyError: ssl_verify = True try: ca_certs = config.get(b"http", b"sslCAInfo") except KeyError: ca_certs = None if user_agent is None: user_agent = default_user_agent_string() headers = {"User-agent": user_agent} kwargs = {} if ssl_verify is True: kwargs['cert_reqs'] = "CERT_REQUIRED" elif ssl_verify is False: kwargs['cert_reqs'] = 'CERT_NONE' else: # Default to SSL verification kwargs['cert_reqs'] = "CERT_REQUIRED" if ca_certs is not None: kwargs['ca_certs'] = ca_certs kwargs.update(override_kwargs) # Try really hard to find a SSL certificate path if 'ca_certs' not in kwargs and kwargs.get('cert_reqs') != 'CERT_NONE': try: import certifi except ImportError: pass else: kwargs['ca_certs'] = certifi.where() import urllib3 if proxy_server is not None: if proxy_manager_cls is None: proxy_manager_cls = urllib3.ProxyManager # `urllib3` requires a `str` object in both Python 2 and 3, while # `ConfigDict` coerces entries to `bytes` on Python 3. Compensate. if not isinstance(proxy_server, str): proxy_server = proxy_server.decode() manager = proxy_manager_cls(proxy_server, headers=headers, **kwargs) else: if pool_manager_cls is None: pool_manager_cls = urllib3.PoolManager manager = pool_manager_cls(headers=headers, **kwargs) return manager class HttpGitClient(GitClient): def __init__(self, base_url, dumb=None, pool_manager=None, config=None, username=None, password=None, **kwargs): self._base_url = base_url.rstrip("/") + "/" self._username = username self._password = password self.dumb = dumb if pool_manager is None: self.pool_manager = default_urllib3_manager(config) else: self.pool_manager = pool_manager if username is not None: # No escaping needed: ":" is not allowed in username: # https://tools.ietf.org/html/rfc2617#section-2 credentials = "%s:%s" % (username, password) import urllib3.util basic_auth = urllib3.util.make_headers(basic_auth=credentials) self.pool_manager.headers.update(basic_auth) GitClient.__init__(self, **kwargs) def get_url(self, path): return self._get_url(path).rstrip("/") @classmethod def from_parsedurl(cls, parsedurl, **kwargs): password = parsedurl.password if password is not None: kwargs['password'] = urlunquote(password) username = parsedurl.username if username is not None: kwargs['username'] = urlunquote(username) netloc = parsedurl.hostname if parsedurl.port: netloc = "%s:%s" % (netloc, parsedurl.port) if parsedurl.username: netloc = "%s@%s" % (parsedurl.username, netloc) parsedurl = parsedurl._replace(netloc=netloc) return cls(urlunparse(parsedurl), **kwargs) def __repr__(self): return "%s(%r, dumb=%r)" % ( type(self).__name__, self._base_url, self.dumb) def _get_url(self, path): if not isinstance(path, str): # urllib3.util.url._encode_invalid_chars() converts the path back # to bytes using the utf-8 codec. path = path.decode('utf-8') return urljoin(self._base_url, path).rstrip("/") + "/" def _http_request(self, url, headers=None, data=None, allow_compression=False): """Perform HTTP request. Args: url: Request URL. headers: Optional custom headers to override defaults. data: Request data. allow_compression: Allow GZipped communication. Returns: Tuple (`response`, `read`), where response is an `urllib3` response object with additional `content_type` and `redirect_location` properties, and `read` is a consumable read method for the response data. """ req_headers = self.pool_manager.headers.copy() if headers is not None: req_headers.update(headers) req_headers["Pragma"] = "no-cache" if allow_compression: req_headers["Accept-Encoding"] = "gzip" else: req_headers["Accept-Encoding"] = "identity" if data is None: resp = self.pool_manager.request("GET", url, headers=req_headers) else: resp = self.pool_manager.request("POST", url, headers=req_headers, body=data) if resp.status == 404: raise NotGitRepository() elif resp.status != 200: raise GitProtocolError("unexpected http resp %d for %s" % (resp.status, url)) # TODO: Optimization available by adding `preload_content=False` to the # request and just passing the `read` method on instead of going via # `BytesIO`, if we can guarantee that the entire response is consumed # before issuing the next to still allow for connection reuse from the # pool. read = BytesIO(resp.data).read resp.content_type = resp.getheader("Content-Type") # Check if geturl() is available (urllib3 version >= 1.23) try: resp_url = resp.geturl() except AttributeError: # get_redirect_location() is available for urllib3 >= 1.1 resp.redirect_location = resp.get_redirect_location() else: resp.redirect_location = resp_url if resp_url != url else '' return resp, read def _discover_references(self, service, base_url): assert base_url[-1] == "/" tail = "info/refs" headers = {"Accept": "*/*"} if self.dumb is not True: tail += "?service=%s" % service.decode('ascii') url = urljoin(base_url, tail) resp, read = self._http_request(url, headers, allow_compression=True) if resp.redirect_location: # Something changed (redirect!), so let's update the base URL if not resp.redirect_location.endswith(tail): raise GitProtocolError( "Redirected from URL %s to URL %s without %s" % ( url, resp.redirect_location, tail)) base_url = resp.redirect_location[:-len(tail)] try: self.dumb = not resp.content_type.startswith("application/x-git-") if not self.dumb: proto = Protocol(read, None) # The first line should mention the service try: [pkt] = list(proto.read_pkt_seq()) except ValueError: raise GitProtocolError( "unexpected number of packets received") if pkt.rstrip(b'\n') != (b'# service=' + service): raise GitProtocolError( "unexpected first line %r from smart server" % pkt) return read_pkt_refs(proto) + (base_url, ) else: return read_info_refs(resp), set(), base_url finally: resp.close() def _smart_request(self, service, url, data): assert url[-1] == "/" url = urljoin(url, service) result_content_type = "application/x-%s-result" % service headers = { "Content-Type": "application/x-%s-request" % service, "Accept": result_content_type, "Content-Length": str(len(data)), } resp, read = self._http_request(url, headers, data) if resp.content_type != result_content_type: raise GitProtocolError("Invalid content-type from server: %s" % resp.content_type) return resp, read def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receives dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) generate_pack_data: Function that can return a tuple with number of elements and pack data to upload. progress: Optional progress function Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data UpdateRefsError: if the server supports report-status and rejects ref updates """ url = self._get_url(path) old_refs, server_capabilities, url = self._discover_references( b"git-receive-pack", url) negotiated_capabilities = self._negotiate_receive_pack_capabilities( server_capabilities) negotiated_capabilities.add(capability_agent()) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() new_refs = update_refs(dict(old_refs)) if new_refs is None: # Determine wants function is aborting the push. return old_refs if self.dumb: raise NotImplementedError(self.fetch_pack) req_data = BytesIO() req_proto = Protocol(None, req_data.write) (have, want) = self._handle_receive_pack_head( req_proto, negotiated_capabilities, old_refs, new_refs) if not want and set(new_refs.items()).issubset(set(old_refs.items())): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) if pack_data_count: write_pack_data(req_proto.write_file(), pack_data_count, pack_data) resp, read = self._smart_request("git-receive-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) self._handle_receive_pack_tail( resp_proto, negotiated_capabilities, progress) return new_refs finally: resp.close() def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Path to fetch from determine_wants: Callback that returns list of commits to fetch graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Depth for request Returns: FetchPackResult object """ url = self._get_url(path) refs, server_capabilities, url = self._discover_references( b"git-upload-pack", url) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) wants = determine_wants(refs) if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: return FetchPackResult(refs, symrefs, agent) if self.dumb: raise NotImplementedError(self.send_pack) req_data = BytesIO() req_proto = Protocol(None, req_data.write) (new_shallow, new_unshallow) = self._handle_upload_pack_head( req_proto, negotiated_capabilities, graph_walker, wants, can_read=None, depth=depth) resp, read = self._smart_request( "git-upload-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) if new_shallow is None and new_unshallow is None: (new_shallow, new_unshallow) = _read_shallow_updates( resp_proto) self._handle_upload_pack_tail( resp_proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult( refs, symrefs, agent, new_shallow, new_unshallow) 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. Args: url: URL to open (a unicode string) config: Optional config object thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. Returns: Tuple with client instance and relative path. """ parsed = urlparse(url) if parsed.scheme == 'git': return (TCPGitClient.from_parsedurl(parsed, **kwargs), parsed.path) elif parsed.scheme in ('git+ssh', 'ssh'): return SSHGitClient.from_parsedurl(parsed, **kwargs), parsed.path elif parsed.scheme in ('http', 'https'): return HttpGitClient.from_parsedurl( parsed, config=config, **kwargs), parsed.path elif parsed.scheme == 'file': return default_local_git_client_cls.from_parsedurl( parsed, **kwargs), parsed.path raise ValueError("unknown scheme '%s'" % parsed.scheme) def parse_rsync_url(location): """Parse a rsync-style URL. """ if ':' in location and '@' not in location: # SSH with no user@, zero or one leading slash. (host, path) = location.split(':', 1) user = None elif ':' in location: # SSH with user@host:foo. user_host, path = location.split(':', 1) if '@' in user_host: user, host = user_host.rsplit('@', 1) else: user = None host = user_host else: raise ValueError('not a valid rsync-style URL') return (user, host, path) def get_transport_and_path(location, **kwargs): """Obtain a git client from a URL. Args: location: URL or path (a string) config: Optional config object thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. Returns: Tuple with client instance and relative path. """ # First, try to parse it as a URL try: return get_transport_and_path_from_url(location, **kwargs) except ValueError: pass if (sys.platform == 'win32' and location[0].isalpha() and location[1:3] == ':\\'): # Windows local path return default_local_git_client_cls(**kwargs), location try: (username, hostname, path) = parse_rsync_url(location) except ValueError: # Otherwise, assume it's a local path. return default_local_git_client_cls(**kwargs), location else: return SSHGitClient(hostname, username=username, **kwargs), path DEFAULT_GIT_CREDENTIALS_PATHS = [ os.path.expanduser('~/.git-credentials'), get_xdg_config_home_path('git', 'credentials')] def get_credentials_from_store(scheme, hostname, username=None, fnames=DEFAULT_GIT_CREDENTIALS_PATHS): for fname in fnames: try: with open(fname, 'rb') as f: for line in f: parsed_line = urlparse.urlparse(line) if (parsed_line.scheme == scheme and parsed_line.hostname == hostname and (username is None or parsed_line.username == username)): return parsed_line.username, parsed_line.password except OSError as e: if e.errno != errno.ENOENT: raise # If the file doesn't exist, try the next one. continue diff --git a/dulwich/contrib/swift.py b/dulwich/contrib/swift.py index cc87f546..bb29f597 100644 --- a/dulwich/contrib/swift.py +++ b/dulwich/contrib/swift.py @@ -1,1047 +1,1046 @@ # swift.py -- Repo implementation atop OpenStack SWIFT # Copyright (C) 2013 eNovance SAS # # Author: Fabien Boucher # # 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. # """Repo implementation atop OpenStack SWIFT.""" # TODO: Refactor to share more code with dulwich/repo.py. # TODO(fbo): Second attempt to _send() must be notified via real log # TODO(fbo): More logs for operations import os import stat import zlib import tempfile import posixpath import urllib.parse as urlparse from io import BytesIO from configparser import ConfigParser from geventhttpclient import HTTPClient from dulwich.greenthreads import ( GreenThreadsMissingObjectFinder, GreenThreadsObjectStoreIterator, ) from dulwich.lru_cache import LRUSizeCache from dulwich.objects import ( Blob, Commit, Tree, Tag, S_ISGITLINK, ) from dulwich.object_store import ( PackBasedObjectStore, PACKDIR, INFODIR, ) from dulwich.pack import ( PackData, Pack, PackIndexer, PackStreamCopier, write_pack_header, compute_file_sha, iter_sha1, write_pack_index_v2, load_pack_index_file, read_pack_header, _compute_object_size, unpack_object, write_pack_object, ) from dulwich.protocol import TCP_GIT_PORT from dulwich.refs import ( InfoRefsContainer, read_info_refs, write_info_refs, ) from dulwich.repo import ( BaseRepo, OBJECTDIR, ) from dulwich.server import ( Backend, TCPGitServer, ) import json import sys """ # Configuration file sample [swift] # Authentication URL (Keystone or Swift) auth_url = http://127.0.0.1:5000/v2.0 # Authentication version to use auth_ver = 2 # The tenant and username separated by a semicolon username = admin;admin # The user password password = pass # The Object storage region to use (auth v2) (Default RegionOne) region_name = RegionOne # The Object storage endpoint URL to use (auth v2) (Default internalURL) endpoint_type = internalURL # Concurrency to use for parallel tasks (Default 10) concurrency = 10 # Size of the HTTP pool (Default 10) http_pool_length = 10 # Timeout delay for HTTP connections (Default 20) http_timeout = 20 # Chunk size to read from pack (Bytes) (Default 12228) chunk_length = 12228 # Cache size (MBytes) (Default 20) cache_length = 20 """ class PackInfoObjectStoreIterator(GreenThreadsObjectStoreIterator): def __len__(self): while len(self.finder.objects_to_send): for _ in range(0, len(self.finder.objects_to_send)): sha = self.finder.next() self._shas.append(sha) return len(self._shas) class PackInfoMissingObjectFinder(GreenThreadsMissingObjectFinder): def next(self): while True: if not self.objects_to_send: return None (sha, name, leaf) = self.objects_to_send.pop() if sha not in self.sha_done: break if not leaf: info = self.object_store.pack_info_get(sha) if info[0] == Commit.type_num: self.add_todo([(info[2], "", False)]) elif info[0] == Tree.type_num: self.add_todo([tuple(i) for i in info[1]]) elif info[0] == Tag.type_num: self.add_todo([(info[1], None, False)]) if sha in self._tagged: self.add_todo([(self._tagged[sha], None, True)]) self.sha_done.add(sha) self.progress("counting objects: %d\r" % len(self.sha_done)) return (sha, name) def load_conf(path=None, file=None): """Load configuration in global var CONF Args: path: The path to the configuration file file: If provided read instead the file like object """ conf = ConfigParser() if file: try: conf.read_file(file, path) except AttributeError: # read_file only exists in Python3 conf.readfp(file) return conf confpath = None if not path: try: confpath = os.environ['DULWICH_SWIFT_CFG'] except KeyError: raise Exception("You need to specify a configuration file") else: confpath = path if not os.path.isfile(confpath): raise Exception("Unable to read configuration file %s" % confpath) conf.read(confpath) return conf def swift_load_pack_index(scon, filename): """Read a pack index file from Swift Args: scon: a `SwiftConnector` instance filename: Path to the index file objectise Returns: a `PackIndexer` instance """ with scon.get_object(filename) as f: return load_pack_index_file(filename, f) def pack_info_create(pack_data, pack_index): pack = Pack.from_objects(pack_data, pack_index) info = {} for obj in pack.iterobjects(): # Commit if obj.type_num == Commit.type_num: info[obj.id] = (obj.type_num, obj.parents, obj.tree) # Tree elif obj.type_num == Tree.type_num: shas = [(s, n, not stat.S_ISDIR(m)) for n, m, s in obj.items() if not S_ISGITLINK(m)] info[obj.id] = (obj.type_num, shas) # Blob elif obj.type_num == Blob.type_num: info[obj.id] = None # Tag elif obj.type_num == Tag.type_num: info[obj.id] = (obj.type_num, obj.object[1]) return zlib.compress(json.dumps(info)) def load_pack_info(filename, scon=None, file=None): if not file: f = scon.get_object(filename) else: f = file if not f: return None try: return json.loads(zlib.decompress(f.read())) finally: f.close() class SwiftException(Exception): pass class SwiftConnector(object): """A Connector to swift that manage authentication and errors catching """ def __init__(self, root, conf): """ Initialize a SwiftConnector Args: root: The swift container that will act as Git bare repository conf: A ConfigParser Object """ self.conf = conf self.auth_ver = self.conf.get("swift", "auth_ver") if self.auth_ver not in ["1", "2"]: raise NotImplementedError( "Wrong authentication version use either 1 or 2") self.auth_url = self.conf.get("swift", "auth_url") self.user = self.conf.get("swift", "username") self.password = self.conf.get("swift", "password") self.concurrency = self.conf.getint('swift', 'concurrency') or 10 self.http_timeout = self.conf.getint('swift', 'http_timeout') or 20 self.http_pool_length = \ self.conf.getint('swift', 'http_pool_length') or 10 self.region_name = self.conf.get("swift", "region_name") or "RegionOne" self.endpoint_type = \ self.conf.get("swift", "endpoint_type") or "internalURL" self.cache_length = self.conf.getint("swift", "cache_length") or 20 self.chunk_length = self.conf.getint("swift", "chunk_length") or 12228 self.root = root block_size = 1024 * 12 # 12KB if self.auth_ver == "1": self.storage_url, self.token = self.swift_auth_v1() else: self.storage_url, self.token = self.swift_auth_v2() token_header = {'X-Auth-Token': str(self.token)} self.httpclient = \ HTTPClient.from_url(str(self.storage_url), concurrency=self.http_pool_length, block_size=block_size, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, headers=token_header) self.base_path = str(posixpath.join( urlparse.urlparse(self.storage_url).path, self.root)) def swift_auth_v1(self): self.user = self.user.replace(";", ":") auth_httpclient = HTTPClient.from_url( self.auth_url, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, ) headers = {'X-Auth-User': self.user, 'X-Auth-Key': self.password} path = urlparse.urlparse(self.auth_url).path ret = auth_httpclient.request('GET', path, headers=headers) # Should do something with redirections (301 in my case) if ret.status_code < 200 or ret.status_code >= 300: raise SwiftException('AUTH v1.0 request failed on ' + '%s with error code %s (%s)' % (str(auth_httpclient.get_base_url()) + path, ret.status_code, str(ret.items()))) storage_url = ret['X-Storage-Url'] token = ret['X-Auth-Token'] return storage_url, token def swift_auth_v2(self): self.tenant, self.user = self.user.split(';') auth_dict = {} auth_dict['auth'] = {'passwordCredentials': { 'username': self.user, 'password': self.password, }, 'tenantName': self.tenant} auth_json = json.dumps(auth_dict) headers = {'Content-Type': 'application/json'} auth_httpclient = HTTPClient.from_url( self.auth_url, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, ) path = urlparse.urlparse(self.auth_url).path if not path.endswith('tokens'): path = posixpath.join(path, 'tokens') ret = auth_httpclient.request('POST', path, body=auth_json, headers=headers) if ret.status_code < 200 or ret.status_code >= 300: raise SwiftException('AUTH v2.0 request failed on ' + '%s with error code %s (%s)' % (str(auth_httpclient.get_base_url()) + path, ret.status_code, str(ret.items()))) auth_ret_json = json.loads(ret.read()) token = auth_ret_json['access']['token']['id'] catalogs = auth_ret_json['access']['serviceCatalog'] object_store = [o_store for o_store in catalogs if o_store['type'] == 'object-store'][0] endpoints = object_store['endpoints'] endpoint = [endp for endp in endpoints if endp["region"] == self.region_name][0] return endpoint[self.endpoint_type], token def test_root_exists(self): """Check that Swift container exist Returns: True if exist or None it not """ ret = self.httpclient.request('HEAD', self.base_path) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('HEAD request failed with error code %s' % ret.status_code) return True def create_root(self): """Create the Swift container Raises: SwiftException: if unable to create """ if not self.test_root_exists(): ret = self.httpclient.request('PUT', self.base_path) if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('PUT request failed with error code %s' % ret.status_code) def get_container_objects(self): """Retrieve objects list in a container Returns: A list of dict that describe objects or None if container does not exist """ qs = '?format=json' path = self.base_path + qs ret = self.httpclient.request('GET', path) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('GET request failed with error code %s' % ret.status_code) content = ret.read() return json.loads(content) def get_object_stat(self, name): """Retrieve object stat Args: name: The object name Returns: A dict that describe the object or None if object does not exist """ path = self.base_path + '/' + name ret = self.httpclient.request('HEAD', path) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('HEAD request failed with error code %s' % ret.status_code) resp_headers = {} for header, value in ret.items(): resp_headers[header.lower()] = value return resp_headers def put_object(self, name, content): """Put an object Args: name: The object name content: A file object Raises: SwiftException: if unable to create """ content.seek(0) data = content.read() path = self.base_path + '/' + name headers = {'Content-Length': str(len(data))} def _send(): ret = self.httpclient.request('PUT', path, body=data, headers=headers) return ret try: # Sometime got Broken Pipe - Dirty workaround ret = _send() except Exception: # Second attempt work ret = _send() if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('PUT request failed with error code %s' % ret.status_code) def get_object(self, name, range=None): """Retrieve an object Args: name: The object name range: A string range like "0-10" to retrieve specified bytes in object content Returns: A file like instance or bytestring if range is specified """ headers = {} if range: headers['Range'] = 'bytes=%s' % range path = self.base_path + '/' + name ret = self.httpclient.request('GET', path, headers=headers) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('GET request failed with error code %s' % ret.status_code) content = ret.read() if range: return content return BytesIO(content) def del_object(self, name): """Delete an object Args: name: The object name Raises: SwiftException: if unable to delete """ path = self.base_path + '/' + name ret = self.httpclient.request('DELETE', path) if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('DELETE request failed with error code %s' % ret.status_code) def del_root(self): """Delete the root container by removing container content Raises: SwiftException: if unable to delete """ for obj in self.get_container_objects(): self.del_object(obj['name']) ret = self.httpclient.request('DELETE', self.base_path) if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('DELETE request failed with error code %s' % ret.status_code) class SwiftPackReader(object): """A SwiftPackReader that mimic read and sync method The reader allows to read a specified amount of bytes from a given offset of a Swift object. A read offset is kept internaly. The reader will read from Swift a specified amount of data to complete its internal buffer. chunk_length specifiy the amount of data to read from Swift. """ def __init__(self, scon, filename, pack_length): """Initialize a SwiftPackReader Args: scon: a `SwiftConnector` instance filename: the pack filename pack_length: The size of the pack object """ self.scon = scon self.filename = filename self.pack_length = pack_length self.offset = 0 self.base_offset = 0 self.buff = b'' self.buff_length = self.scon.chunk_length def _read(self, more=False): if more: self.buff_length = self.buff_length * 2 offset = self.base_offset r = min(self.base_offset + self.buff_length, self.pack_length) ret = self.scon.get_object(self.filename, range="%s-%s" % (offset, r)) self.buff = ret def read(self, length): """Read a specified amount of Bytes form the pack object Args: length: amount of bytes to read Returns: a bytestring """ end = self.offset+length if self.base_offset + end > self.pack_length: data = self.buff[self.offset:] self.offset = end return data if end > len(self.buff): # Need to read more from swift self._read(more=True) return self.read(length) data = self.buff[self.offset:end] self.offset = end return data def seek(self, offset): """Seek to a specified offset Args: offset: the offset to seek to """ self.base_offset = offset self._read() self.offset = 0 def read_checksum(self): """Read the checksum from the pack Returns: the checksum bytestring """ return self.scon.get_object(self.filename, range="-20") class SwiftPackData(PackData): """The data contained in a packfile. We use the SwiftPackReader to read bytes from packs stored in Swift using the Range header feature of Swift. """ def __init__(self, scon, filename): """ Initialize a SwiftPackReader Args: scon: a `SwiftConnector` instance filename: the pack filename """ self.scon = scon self._filename = filename self._header_size = 12 headers = self.scon.get_object_stat(self._filename) self.pack_length = int(headers['content-length']) pack_reader = SwiftPackReader(self.scon, self._filename, self.pack_length) (version, self._num_objects) = read_pack_header(pack_reader.read) self._offset_cache = LRUSizeCache(1024*1024*self.scon.cache_length, compute_size=_compute_object_size) self.pack = None def get_object_at(self, offset): if offset in self._offset_cache: return self._offset_cache[offset] assert offset >= self._header_size pack_reader = SwiftPackReader(self.scon, self._filename, self.pack_length) pack_reader.seek(offset) unpacked, _ = unpack_object(pack_reader.read) return (unpacked.pack_type_num, unpacked._obj()) def get_stored_checksum(self): pack_reader = SwiftPackReader(self.scon, self._filename, self.pack_length) return pack_reader.read_checksum() def close(self): pass class SwiftPack(Pack): """A Git pack object. Same implementation as pack.Pack except that _idx_load and _data_load are bounded to Swift version of load_pack_index and PackData. """ def __init__(self, *args, **kwargs): self.scon = kwargs['scon'] del kwargs['scon'] super(SwiftPack, self).__init__(*args, **kwargs) self._pack_info_path = self._basename + '.info' self._pack_info = None self._pack_info_load = lambda: load_pack_info(self._pack_info_path, self.scon) self._idx_load = lambda: swift_load_pack_index(self.scon, self._idx_path) self._data_load = lambda: SwiftPackData(self.scon, self._data_path) @property def pack_info(self): """The pack data object being used.""" if self._pack_info is None: self._pack_info = self._pack_info_load() return self._pack_info class SwiftObjectStore(PackBasedObjectStore): """A Swift Object Store Allow to manage a bare Git repository from Openstack Swift. This object store only supports pack files and not loose objects. """ def __init__(self, scon): """Open a Swift object store. Args: scon: A `SwiftConnector` instance """ super(SwiftObjectStore, self).__init__() self.scon = scon self.root = self.scon.root self.pack_dir = posixpath.join(OBJECTDIR, PACKDIR) self._alternates = None def _update_pack_cache(self): objects = self.scon.get_container_objects() pack_files = [o['name'].replace(".pack", "") for o in objects if o['name'].endswith(".pack")] ret = [] for basename in pack_files: pack = SwiftPack(basename, scon=self.scon) self._pack_cache[basename] = pack ret.append(pack) return ret def _iter_loose_objects(self): """Loose objects are not supported by this repository """ return [] def iter_shas(self, finder): """An iterator over pack's ObjectStore. Returns: a `ObjectStoreIterator` or `GreenThreadsObjectStoreIterator` instance if gevent is enabled """ shas = iter(finder.next, None) return PackInfoObjectStoreIterator( self, shas, finder, self.scon.concurrency) def find_missing_objects(self, *args, **kwargs): kwargs['concurrency'] = self.scon.concurrency return PackInfoMissingObjectFinder(self, *args, **kwargs) def pack_info_get(self, sha): for pack in self.packs: if sha in pack: return pack.pack_info[sha] def _collect_ancestors(self, heads, common=set()): def _find_parents(commit): for pack in self.packs: if commit in pack: try: parents = pack.pack_info[commit][1] except KeyError: # Seems to have no parents return [] return parents bases = set() commits = set() queue = [] queue.extend(heads) while queue: e = queue.pop(0) if e in common: bases.add(e) elif e not in commits: commits.add(e) parents = _find_parents(e) queue.extend(parents) return (commits, bases) def add_pack(self): """Add a new pack to this object store. Returns: Fileobject to write to and a commit function to call when the pack is finished. """ f = BytesIO() def commit(): f.seek(0) pack = PackData(file=f, filename="") entries = pack.sorted_entries() if len(entries): basename = posixpath.join(self.pack_dir, "pack-%s" % iter_sha1(entry[0] for entry in entries)) index = BytesIO() write_pack_index_v2(index, entries, pack.get_stored_checksum()) self.scon.put_object(basename + ".pack", f) f.close() self.scon.put_object(basename + ".idx", index) index.close() final_pack = SwiftPack(basename, scon=self.scon) final_pack.check_length_and_checksum() self._add_cached_pack(basename, final_pack) return final_pack else: return None def abort(): pass return f, commit, abort def add_object(self, obj): self.add_objects([(obj, None), ]) def _pack_cache_stale(self): return False def _get_loose_object(self, sha): return None def add_thin_pack(self, read_all, read_some): """Read a thin pack Read it from a stream and complete it in a temporary file. Then the pack and the corresponding index file are uploaded to Swift. """ fd, path = tempfile.mkstemp(prefix='tmp_pack_') f = os.fdopen(fd, 'w+b') try: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() return self._complete_thin_pack(f, path, copier, indexer) finally: f.close() os.unlink(path) def _complete_thin_pack(self, f, path, copier, indexer): entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Must flush before reading (http://bugs.python.org/issue3207) f.flush() # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Must reposition before writing (http://bugs.python.org/issue3207) f.seek(0, os.SEEK_CUR) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) offset = f.tell() crc32 = write_pack_object(f, type_num, data, sha=new_sha) entries.append((ext_sha, offset, crc32)) pack_sha = new_sha.digest() f.write(pack_sha) f.flush() # Move the pack in. entries.sort() pack_base_name = posixpath.join( self.pack_dir, - 'pack-' + iter_sha1(e[0] for e in entries).decode( - sys.getfilesystemencoding())) + 'pack-' + os.fsdecode(iter_sha1(e[0] for e in entries))) self.scon.put_object(pack_base_name + '.pack', f) # Write the index. filename = pack_base_name + '.idx' index_file = BytesIO() write_pack_index_v2(index_file, entries, pack_sha) self.scon.put_object(filename, index_file) # Write pack info. f.seek(0) pack_data = PackData(filename="", file=f) index_file.seek(0) pack_index = load_pack_index_file('', index_file) serialized_pack_info = pack_info_create(pack_data, pack_index) f.close() index_file.close() pack_info_file = BytesIO(serialized_pack_info) filename = pack_base_name + '.info' self.scon.put_object(filename, pack_info_file) pack_info_file.close() # Add the pack to the store and return it. final_pack = SwiftPack(pack_base_name, scon=self.scon) final_pack.check_length_and_checksum() self._add_cached_pack(pack_base_name, final_pack) return final_pack class SwiftInfoRefsContainer(InfoRefsContainer): """Manage references in info/refs object. """ def __init__(self, scon, store): self.scon = scon self.filename = 'info/refs' self.store = store f = self.scon.get_object(self.filename) if not f: f = BytesIO(b'') super(SwiftInfoRefsContainer, self).__init__(f) def _load_check_ref(self, name, old_ref): self._check_refname(name) f = self.scon.get_object(self.filename) if not f: return {} refs = read_info_refs(f) if old_ref is not None: if refs[name] != old_ref: return False return refs def _write_refs(self, refs): f = BytesIO() f.writelines(write_info_refs(refs, self.store)) self.scon.put_object(self.filename, f) def set_if_equals(self, name, old_ref, new_ref): """Set a refname to new_ref only if it currently equals old_ref. """ if name == 'HEAD': return True refs = self._load_check_ref(name, old_ref) if not isinstance(refs, dict): return False refs[name] = new_ref self._write_refs(refs) self._refs[name] = new_ref return True def remove_if_equals(self, name, old_ref): """Remove a refname only if it currently equals old_ref. """ if name == 'HEAD': return True refs = self._load_check_ref(name, old_ref) if not isinstance(refs, dict): return False del refs[name] self._write_refs(refs) del self._refs[name] return True def allkeys(self): try: self._refs['HEAD'] = self._refs['refs/heads/master'] except KeyError: pass return self._refs.keys() class SwiftRepo(BaseRepo): def __init__(self, root, conf): """Init a Git bare Repository on top of a Swift container. References are managed in info/refs objects by `SwiftInfoRefsContainer`. The root attribute is the Swift container that contain the Git bare repository. Args: root: The container which contains the bare repo conf: A ConfigParser object """ self.root = root.lstrip('/') self.conf = conf self.scon = SwiftConnector(self.root, self.conf) objects = self.scon.get_container_objects() if not objects: raise Exception('There is not any GIT repo here : %s' % self.root) objects = [o['name'].split('/')[0] for o in objects] if OBJECTDIR not in objects: raise Exception('This repository (%s) is not bare.' % self.root) self.bare = True self._controldir = self.root object_store = SwiftObjectStore(self.scon) refs = SwiftInfoRefsContainer(self.scon, object_store) BaseRepo.__init__(self, object_store, refs) def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ return False def _put_named_file(self, filename, contents): """Put an object in a Swift container Args: filename: the path to the object to put on Swift contents: the content as bytestring """ with BytesIO() as f: f.write(contents) self.scon.put_object(filename, f) @classmethod def init_bare(cls, scon, conf): """Create a new bare repository. Args: scon: a `SwiftConnector` instance conf: a ConfigParser object Returns: a `SwiftRepo` instance """ scon.create_root() for obj in [posixpath.join(OBJECTDIR, PACKDIR), posixpath.join(INFODIR, 'refs')]: scon.put_object(obj, BytesIO(b'')) ret = cls(scon.root, conf) ret._init_files(True) return ret class SwiftSystemBackend(Backend): def __init__(self, logger, conf): self.conf = conf self.logger = logger def open_repository(self, path): self.logger.info('opening repository at %s', path) return SwiftRepo(path, self.conf) def cmd_daemon(args): """Entry point for starting a TCP git server.""" import optparse parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="127.0.0.1", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") parser.add_option("-c", "--swift_config", dest="swift_config", default="", help="Path to the configuration file for Swift backend.") options, args = parser.parse_args(args) try: import gevent import geventhttpclient # noqa: F401 except ImportError: print("gevent and geventhttpclient libraries are mandatory " " for use the Swift backend.") sys.exit(1) import gevent.monkey gevent.monkey.patch_socket() from dulwich import log_utils logger = log_utils.getLogger(__name__) conf = load_conf(options.swift_config) backend = SwiftSystemBackend(logger, conf) log_utils.default_logging_config() server = TCPGitServer(backend, options.listen_address, port=options.port) server.serve_forever() def cmd_init(args): import optparse parser = optparse.OptionParser() parser.add_option("-c", "--swift_config", dest="swift_config", default="", help="Path to the configuration file for Swift backend.") options, args = parser.parse_args(args) conf = load_conf(options.swift_config) if args == []: parser.error("missing repository name") repo = args[0] scon = SwiftConnector(repo, conf) SwiftRepo.init_bare(scon, conf) def main(argv=sys.argv): commands = { "init": cmd_init, "daemon": cmd_daemon, } if len(sys.argv) < 2: print("Usage: %s <%s> [OPTIONS...]" % ( sys.argv[0], "|".join(commands.keys()))) sys.exit(1) cmd = sys.argv[1] if cmd not in commands: print("No such subcommand: %s" % cmd) sys.exit(1) commands[cmd](sys.argv[2:]) if __name__ == '__main__': main() diff --git a/dulwich/ignore.py b/dulwich/ignore.py index a1154af1..72396401 100644 --- a/dulwich/ignore.py +++ b/dulwich/ignore.py @@ -1,374 +1,374 @@ # Copyright (C) 2017 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. # """Parsing of gitignore files. For details for the matching rules, see https://git-scm.com/docs/gitignore """ import os.path import re import sys from dulwich.config import get_xdg_config_home_path def _translate_segment(segment): if segment == b"*": return b'[^/]+' res = b"" i, n = 0, len(segment) while i < n: c = segment[i:i+1] i = i+1 if c == b'*': res += b'[^/]*' elif c == b'?': res += b'[^/]' elif c == b'[': j = i if j < n and segment[j:j+1] == b'!': j = j+1 if j < n and segment[j:j+1] == b']': j = j+1 while j < n and segment[j:j+1] != b']': j = j+1 if j >= n: res += b'\\[' else: stuff = segment[i:j].replace(b'\\', b'\\\\') i = j+1 if stuff.startswith(b'!'): stuff = b'^' + stuff[1:] elif stuff.startswith(b'^'): stuff = b'\\' + stuff res += b'[' + stuff + b']' else: res += re.escape(c) return res def translate(pat): """Translate a shell PATTERN to a regular expression. There is no way to quote meta-characters. Originally copied from fnmatch in Python 2.7, but modified for Dulwich to cope with features in Git ignore patterns. """ res = b'(?ms)' if b'/' not in pat[:-1]: # If there's no slash, this is a filename-based match res += b'(.*/)?' if pat.startswith(b'**/'): # Leading **/ pat = pat[2:] res += b'(.*/)?' if pat.startswith(b'/'): pat = pat[1:] for i, segment in enumerate(pat.split(b'/')): if segment == b'**': res += b'(/.*)?' continue else: res += ((re.escape(b'/') if i > 0 else b'') + _translate_segment(segment)) if not pat.endswith(b'/'): res += b'/?' return res + b'\\Z' def read_ignore_patterns(f): """Read a git ignore file. Args: f: File-like object to read from Returns: List of patterns """ for line in f: line = line.rstrip(b"\r\n") # Ignore blank lines, they're used for readability. if not line: continue if line.startswith(b'#'): # Comment continue # Trailing spaces are ignored unless they are quoted with a backslash. while line.endswith(b' ') and not line.endswith(b'\\ '): line = line[:-1] line = line.replace(b'\\ ', b' ') yield line def match_pattern(path, pattern, ignorecase=False): """Match a gitignore-style pattern against a path. Args: path: Path to match pattern: Pattern to match ignorecase: Whether to do case-sensitive matching Returns: bool indicating whether the pattern matched """ return Pattern(pattern, ignorecase).match(path) class Pattern(object): """A single ignore pattern.""" def __init__(self, pattern, ignorecase=False): self.pattern = pattern self.ignorecase = ignorecase if pattern[0:1] == b'!': self.is_exclude = False pattern = pattern[1:] else: if pattern[0:1] == b'\\': pattern = pattern[1:] self.is_exclude = True flags = 0 if self.ignorecase: flags = re.IGNORECASE self._re = re.compile(translate(pattern), flags) def __bytes__(self): return self.pattern def __str__(self): - return self.pattern.decode(sys.getfilesystemencoding()) + return os.fsdecode(self.pattern) def __eq__(self, other): return (type(self) == type(other) and self.pattern == other.pattern and self.ignorecase == other.ignorecase) def __repr__(self): return "%s(%s, %r)" % ( type(self).__name__, self.pattern, self.ignorecase) def match(self, path): """Try to match a path against this ignore pattern. Args: path: Path to match (relative to ignore location) Returns: boolean """ return bool(self._re.match(path)) class IgnoreFilter(object): def __init__(self, patterns, ignorecase=False): self._patterns = [] self._ignorecase = ignorecase for pattern in patterns: self.append_pattern(pattern) def append_pattern(self, pattern): """Add a pattern to the set.""" self._patterns.append(Pattern(pattern, self._ignorecase)) def find_matching(self, path): """Yield all matching patterns for path. Args: path: Path to match Returns: Iterator over iterators """ if not isinstance(path, bytes): - path = path.encode(sys.getfilesystemencoding()) + path = os.fsencode(path) for pattern in self._patterns: if pattern.match(path): yield pattern def is_ignored(self, path): """Check whether a path is ignored. For directories, include a trailing slash. Returns: status is None if file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for pattern in self.find_matching(path): status = pattern.is_exclude return status @classmethod def from_path(cls, path, ignorecase=False): with open(path, 'rb') as f: ret = cls(read_ignore_patterns(f), ignorecase) ret._path = path return ret def __repr__(self): if getattr(self, '_path', None) is None: return "<%s>" % (type(self).__name__) else: return "%s.from_path(%r)" % (type(self).__name__, self._path) class IgnoreFilterStack(object): """Check for ignore status in multiple filters.""" def __init__(self, filters): self._filters = filters def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. Args: path: Path to check Returns: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for filter in self._filters: status = filter.is_ignored(path) if status is not None: return status return status def default_user_ignore_filter_path(config): """Return default user ignore filter path. Args: config: A Config object Returns: Path to a global ignore file """ try: return config.get((b'core', ), b'excludesFile') except KeyError: pass return get_xdg_config_home_path('git', 'ignore') class IgnoreFilterManager(object): """Ignore file manager.""" def __init__(self, top_path, global_filters, ignorecase): self._path_filters = {} self._top_path = top_path self._global_filters = global_filters self._ignorecase = ignorecase def __repr__(self): return "%s(%s, %r, %r)" % ( type(self).__name__, self._top_path, self._global_filters, self._ignorecase) def _load_path(self, path): try: return self._path_filters[path] except KeyError: pass p = os.path.join(self._top_path, path, '.gitignore') try: self._path_filters[path] = IgnoreFilter.from_path( p, self._ignorecase) except IOError: self._path_filters[path] = None return self._path_filters[path] def find_matching(self, path): """Find matching patterns for path. Stops after the first ignore file with matches. Args: path: Path to check Returns: Iterator over Pattern instances """ if os.path.isabs(path): raise ValueError('%s is an absolute path' % path) filters = [(0, f) for f in self._global_filters] if os.path.sep != '/': path = path.replace(os.path.sep, '/') parts = path.split('/') for i in range(len(parts)+1): dirname = '/'.join(parts[:i]) for s, f in filters: relpath = '/'.join(parts[s:i]) if i < len(parts): # Paths leading up to the final part are all directories, # so need a trailing slash. relpath += '/' matches = list(f.find_matching(relpath)) if matches: return iter(matches) ignore_filter = self._load_path(dirname) if ignore_filter is not None: filters.insert(0, (i, ignore_filter)) return iter([]) def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. Args: path: Path to check Returns: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ matches = list(self.find_matching(path)) if matches: return matches[-1].is_exclude return None @classmethod def from_repo(cls, repo): """Create a IgnoreFilterManager from a repository. Args: repo: Repository object Returns: A `IgnoreFilterManager` object """ global_filters = [] for p in [ os.path.join(repo.controldir(), 'info', 'exclude'), default_user_ignore_filter_path(repo.get_config_stack())]: try: global_filters.append( IgnoreFilter.from_path(os.path.expanduser(p))) except IOError: pass config = repo.get_config_stack() ignorecase = config.get_boolean((b'core'), (b'ignorecase'), False) return cls(repo.path, global_filters, ignorecase) diff --git a/dulwich/index.py b/dulwich/index.py index f8df3509..c5fc3da1 100644 --- a/dulwich/index.py +++ b/dulwich/index.py @@ -1,848 +1,846 @@ # index.py -- File parser/writer for the git index file # 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. # """Parser for the git index file format.""" import collections import errno import os import stat import struct import sys from dulwich.file import GitFile from dulwich.objects import ( Blob, S_IFGITLINK, S_ISGITLINK, Tree, hex_to_sha, sha_to_hex, ) from dulwich.pack import ( SHA1Reader, SHA1Writer, ) IndexEntry = collections.namedtuple( 'IndexEntry', [ 'ctime', 'mtime', 'dev', 'ino', 'mode', 'uid', 'gid', 'size', 'sha', 'flags']) FLAG_STAGEMASK = 0x3000 FLAG_VALID = 0x8000 FLAG_EXTENDED = 0x4000 def pathsplit(path): """Split a /-delimited path into a directory part and a basename. Args: path: The path to split. Returns: Tuple with directory name and basename """ try: (dirname, basename) = path.rsplit(b"/", 1) except ValueError: return (b"", path) else: return (dirname, basename) def pathjoin(*args): """Join a /-delimited path. """ return b"/".join([p for p in args if p]) def read_cache_time(f): """Read a cache time. Args: f: File-like object to read from Returns: Tuple with seconds and nanoseconds """ return struct.unpack(">LL", f.read(8)) def write_cache_time(f, t): """Write a cache time. Args: f: File-like object to write to t: Time to write (as int, float or tuple with secs and nsecs) """ if isinstance(t, int): t = (t, 0) elif isinstance(t, float): (secs, nsecs) = divmod(t, 1.0) t = (int(secs), int(nsecs * 1000000000)) elif not isinstance(t, tuple): raise TypeError(t) f.write(struct.pack(">LL", *t)) def read_cache_entry(f): """Read an entry from a cache file. Args: f: File-like object to read from Returns: tuple with: device, inode, mode, uid, gid, size, sha, flags """ beginoffset = f.tell() ctime = read_cache_time(f) mtime = read_cache_time(f) (dev, ino, mode, uid, gid, size, sha, flags, ) = \ struct.unpack(">LLLLLL20sH", f.read(20 + 4 * 6 + 2)) name = f.read((flags & 0x0fff)) # Padding: real_size = ((f.tell() - beginoffset + 8) & ~7) f.read((beginoffset + real_size) - f.tell()) return (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha_to_hex(sha), flags & ~0x0fff) def write_cache_entry(f, entry): """Write an index entry to a file. Args: f: File object entry: Entry to write, tuple with: (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) """ beginoffset = f.tell() (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) = entry write_cache_time(f, ctime) write_cache_time(f, mtime) flags = len(name) | (flags & ~0x0fff) f.write(struct.pack( b'>LLLLLL20sH', dev & 0xFFFFFFFF, ino & 0xFFFFFFFF, mode, uid, gid, size, hex_to_sha(sha), flags)) f.write(name) real_size = ((f.tell() - beginoffset + 8) & ~7) f.write(b'\0' * ((beginoffset + real_size) - f.tell())) def read_index(f): """Read an index file, yielding the individual entries.""" header = f.read(4) if header != b'DIRC': raise AssertionError("Invalid index file header: %r" % header) (version, num_entries) = struct.unpack(b'>LL', f.read(4 * 2)) assert version in (1, 2) for i in range(num_entries): yield read_cache_entry(f) def read_index_dict(f): """Read an index file and return it as a dictionary. Args: f: File object to read from """ ret = {} for x in read_index(f): ret[x[0]] = IndexEntry(*x[1:]) return ret def write_index(f, entries): """Write an index file. Args: f: File-like object to write to entries: Iterable over the entries to write """ f.write(b'DIRC') f.write(struct.pack(b'>LL', 2, len(entries))) for x in entries: write_cache_entry(f, x) def write_index_dict(f, entries): """Write an index file based on the contents of a dictionary. """ entries_list = [] for name in sorted(entries): entries_list.append((name,) + tuple(entries[name])) write_index(f, entries_list) def cleanup_mode(mode): """Cleanup a mode value. This will return a mode that can be stored in a tree object. Args: mode: Mode to clean up. """ if stat.S_ISLNK(mode): return stat.S_IFLNK elif stat.S_ISDIR(mode): return stat.S_IFDIR elif S_ISGITLINK(mode): return S_IFGITLINK ret = stat.S_IFREG | 0o644 if mode & 0o100: ret |= 0o111 return ret class Index(object): """A Git Index file.""" def __init__(self, filename): """Open an index file. Args: filename: Path to the index file """ self._filename = filename self.clear() self.read() @property def path(self): return self._filename def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self._filename) def write(self): """Write current contents of index to disk.""" f = GitFile(self._filename, 'wb') try: f = SHA1Writer(f) write_index_dict(f, self._byname) finally: f.close() def read(self): """Read current contents of index from disk.""" if not os.path.exists(self._filename): return f = GitFile(self._filename, 'rb') try: f = SHA1Reader(f) for x in read_index(f): self[x[0]] = IndexEntry(*x[1:]) # FIXME: Additional data? f.read(os.path.getsize(self._filename)-f.tell()-20) f.check_sha() finally: f.close() def __len__(self): """Number of entries in this index file.""" return len(self._byname) def __getitem__(self, name): """Retrieve entry by relative path. Returns: tuple with (ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) """ return self._byname[name] def __iter__(self): """Iterate over the paths in this index.""" return iter(self._byname) def get_sha1(self, path): """Return the (git object) SHA1 for the object at a path.""" return self[path].sha def get_mode(self, path): """Return the POSIX file mode for the object at a path.""" return self[path].mode def iterobjects(self): """Iterate over path, sha, mode tuples for use with commit_tree.""" for path in self: entry = self[path] yield path, entry.sha, cleanup_mode(entry.mode) def iterblobs(self): import warnings warnings.warn('Use iterobjects() instead.', PendingDeprecationWarning) return self.iterobjects() def clear(self): """Remove all contents from this index.""" self._byname = {} def __setitem__(self, name, x): assert isinstance(name, bytes) assert len(x) == 10 # Remove the old entry if any self._byname[name] = IndexEntry(*x) def __delitem__(self, name): assert isinstance(name, bytes) del self._byname[name] def iteritems(self): return self._byname.items() def items(self): return self._byname.items() def update(self, entries): for name, value in entries.items(): self[name] = value def changes_from_tree(self, object_store, tree, want_unchanged=False): """Find the differences between the contents of this index and a tree. Args: object_store: Object store to use for retrieving tree contents tree: SHA1 of the root tree want_unchanged: Whether unchanged files should be reported Returns: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ def lookup_entry(path): entry = self[path] return entry.sha, cleanup_mode(entry.mode) for (name, mode, sha) in changes_from_tree( self._byname.keys(), lookup_entry, object_store, tree, want_unchanged=want_unchanged): yield (name, mode, sha) def commit(self, object_store): """Create a new tree from an index. Args: object_store: Object store to save the tree in Returns: Root tree SHA """ return commit_tree(object_store, self.iterobjects()) def commit_tree(object_store, blobs): """Commit a new tree. Args: object_store: Object store to add trees to blobs: Iterable over blob path, sha, mode entries Returns: SHA1 of the created tree. """ trees = {b'': {}} def add_tree(path): if path in trees: return trees[path] dirname, basename = pathsplit(path) t = add_tree(dirname) assert isinstance(basename, bytes) newtree = {} t[basename] = newtree trees[path] = newtree return newtree for path, sha, mode in blobs: tree_path, basename = pathsplit(path) tree = add_tree(tree_path) tree[basename] = (mode, sha) def build_tree(path): tree = Tree() for basename, entry in trees[path].items(): if isinstance(entry, dict): mode = stat.S_IFDIR sha = build_tree(pathjoin(path, basename)) else: (mode, sha) = entry tree.add(basename, mode, sha) object_store.add_object(tree) return tree.id return build_tree(b'') def commit_index(object_store, index): """Create a new tree from an index. Args: object_store: Object store to save the tree in index: Index file Note: This function is deprecated, use index.commit() instead. Returns: Root tree sha. """ return commit_tree(object_store, index.iterobjects()) def changes_from_tree(names, lookup_entry, object_store, tree, want_unchanged=False): """Find the differences between the contents of a tree and a working copy. Args: names: Iterable of names in the working copy lookup_entry: Function to lookup an entry in the working copy object_store: Object store to use for retrieving tree contents tree: SHA1 of the root tree, or None for an empty tree want_unchanged: Whether unchanged files should be reported Returns: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ # TODO(jelmer): Support a include_trees option other_names = set(names) if tree is not None: for (name, mode, sha) in object_store.iter_tree_contents(tree): try: (other_sha, other_mode) = lookup_entry(name) except KeyError: # Was removed yield ((name, None), (mode, None), (sha, None)) else: other_names.remove(name) if (want_unchanged or other_sha != sha or other_mode != mode): yield ((name, name), (mode, other_mode), (sha, other_sha)) # Mention added files for name in other_names: try: (other_sha, other_mode) = lookup_entry(name) except KeyError: pass else: yield ((None, name), (None, other_mode), (None, other_sha)) def index_entry_from_stat(stat_val, hex_sha, flags, mode=None): """Create a new index entry from a stat value. Args: stat_val: POSIX stat_result instance hex_sha: Hex sha of the object flags: Index flags """ if mode is None: mode = cleanup_mode(stat_val.st_mode) return IndexEntry( stat_val.st_ctime, stat_val.st_mtime, stat_val.st_dev, stat_val.st_ino, mode, stat_val.st_uid, stat_val.st_gid, stat_val.st_size, hex_sha, flags) def build_file_from_blob(blob, mode, target_path, honor_filemode=True): """Build a file or symlink on disk based on a Git object. Args: obj: The git object mode: File mode target_path: Path to write to honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit Returns: stat object for the file """ try: oldstat = os.lstat(target_path) except OSError as e: if e.errno == errno.ENOENT: oldstat = None else: raise contents = blob.as_raw_string() if stat.S_ISLNK(mode): # FIXME: This will fail on Windows. What should we do instead? if oldstat: os.unlink(target_path) if sys.platform == 'win32': # os.readlink on Python3 on Windows requires a unicode string. # TODO(jelmer): Don't assume tree_encoding == fs_encoding tree_encoding = sys.getfilesystemencoding() contents = contents.decode(tree_encoding) target_path = target_path.decode(tree_encoding) os.symlink(contents, target_path) else: if oldstat is not None and oldstat.st_size == len(contents): with open(target_path, 'rb') as f: if f.read() == contents: return oldstat with open(target_path, 'wb') as f: # Write out file f.write(contents) if honor_filemode: os.chmod(target_path, mode) return os.lstat(target_path) INVALID_DOTNAMES = (b".git", b".", b"..", b"") def validate_path_element_default(element): return element.lower() not in INVALID_DOTNAMES def validate_path_element_ntfs(element): stripped = element.rstrip(b". ").lower() if stripped in INVALID_DOTNAMES: return False if stripped == b"git~1": return False return True def validate_path(path, element_validator=validate_path_element_default): """Default path validator that just checks for .git/.""" parts = path.split(b"/") for p in parts: if not element_validator(p): return False else: return True def build_index_from_tree(root_path, index_path, object_store, tree_id, honor_filemode=True, validate_path_element=validate_path_element_default): """Generate and materialize index from a tree Args: tree_id: Tree to materialize root_path: Target dir for materialized index files index_path: Target path for generated index object_store: Non-empty object store holding tree contents honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit validate_path_element: Function to validate path elements to check out; default just refuses .git and .. directories. Note: existing index is wiped and contents are not merged in a working dir. Suitable only for fresh clones. """ index = Index(index_path) if not isinstance(root_path, bytes): - root_path = root_path.encode(sys.getfilesystemencoding()) + root_path = os.fsencode(root_path) for entry in object_store.iter_tree_contents(tree_id): if not validate_path(entry.path, validate_path_element): continue full_path = _tree_to_fs_path(root_path, entry.path) if not os.path.exists(os.path.dirname(full_path)): os.makedirs(os.path.dirname(full_path)) # TODO(jelmer): Merge new index into working tree if S_ISGITLINK(entry.mode): if not os.path.isdir(full_path): os.mkdir(full_path) st = os.lstat(full_path) # TODO(jelmer): record and return submodule paths else: obj = object_store[entry.sha] st = build_file_from_blob( obj, entry.mode, full_path, honor_filemode=honor_filemode) # Add file to index if not honor_filemode or S_ISGITLINK(entry.mode): # we can not use tuple slicing to build a new tuple, # because on windows that will convert the times to # longs, which causes errors further along st_tuple = (entry.mode, st.st_ino, st.st_dev, st.st_nlink, st.st_uid, st.st_gid, st.st_size, st.st_atime, st.st_mtime, st.st_ctime) st = st.__class__(st_tuple) index[entry.path] = index_entry_from_stat(st, entry.sha, 0) index.write() def blob_from_path_and_stat(fs_path, st): """Create a blob from a path and a stat object. Args: fs_path: Full file system path to file st: A stat object Returns: A `Blob` object """ assert isinstance(fs_path, bytes) blob = Blob() if stat.S_ISLNK(st.st_mode): if sys.platform == 'win32': # os.readlink on Python3 on Windows requires a unicode string. # TODO(jelmer): Don't assume tree_encoding == fs_encoding tree_encoding = sys.getfilesystemencoding() fs_path = fs_path.decode(tree_encoding) blob.data = os.readlink(fs_path).encode(tree_encoding) else: blob.data = os.readlink(fs_path) else: with open(fs_path, 'rb') as f: blob.data = f.read() return blob def read_submodule_head(path): """Read the head commit of a submodule. Args: path: path to the submodule Returns: HEAD sha, None if not a valid head/repository """ from dulwich.errors import NotGitRepository from dulwich.repo import Repo # Repo currently expects a "str", so decode if necessary. # TODO(jelmer): Perhaps move this into Repo() ? if not isinstance(path, str): - path = path.decode(sys.getfilesystemencoding()) + path = os.fsdecode(path) try: repo = Repo(path) except NotGitRepository: return None try: return repo.head() except KeyError: return None def _has_directory_changed(tree_path, entry): """Check if a directory has changed after getting an error. When handling an error trying to create a blob from a path, call this function. It will check if the path is a directory. If it's a directory and a submodule, check the submodule head to see if it's has changed. If not, consider the file as changed as Git tracked a file and not a directory. Return true if the given path should be considered as changed and False otherwise or if the path is not a directory. """ # This is actually a directory if os.path.exists(os.path.join(tree_path, b'.git')): # Submodule head = read_submodule_head(tree_path) if entry.sha != head: return True else: # The file was changed to a directory, so consider it removed. return True return False def get_unstaged_changes(index, root_path, filter_blob_callback=None): """Walk through an index and check for differences against working tree. Args: index: index to check root_path: path in which to find files Returns: iterator over paths with unstaged changes """ # For each entry in the index check the sha1 & ensure not staged if not isinstance(root_path, bytes): - root_path = root_path.encode(sys.getfilesystemencoding()) + root_path = os.fsencode(root_path) for tree_path, entry in index.iteritems(): full_path = _tree_to_fs_path(root_path, tree_path) try: st = os.lstat(full_path) if stat.S_ISDIR(st.st_mode): if _has_directory_changed(tree_path, entry): yield tree_path continue if not stat.S_ISREG(st.st_mode) and not stat.S_ISLNK(st.st_mode): continue blob = blob_from_path_and_stat(full_path, st) if filter_blob_callback is not None: blob = filter_blob_callback(blob, tree_path) except EnvironmentError as e: if e.errno == errno.ENOENT: # The file was removed, so we assume that counts as # different from whatever file used to exist. yield tree_path else: raise else: if blob.id != entry.sha: yield tree_path os_sep_bytes = os.sep.encode('ascii') def _tree_to_fs_path(root_path, tree_path): """Convert a git tree path to a file system path. Args: root_path: Root filesystem path tree_path: Git tree path as bytes Returns: File system path. """ assert isinstance(tree_path, bytes) if os_sep_bytes != b'/': sep_corrected_path = tree_path.replace(b'/', os_sep_bytes) else: sep_corrected_path = tree_path return os.path.join(root_path, sep_corrected_path) def _fs_to_tree_path(fs_path, fs_encoding=None): """Convert a file system path to a git tree path. Args: fs_path: File system path. fs_encoding: File system encoding Returns: Git tree path as bytes """ - if fs_encoding is None: - fs_encoding = sys.getfilesystemencoding() if not isinstance(fs_path, bytes): fs_path_bytes = fs_path.encode(fs_encoding) else: fs_path_bytes = fs_path if os_sep_bytes != b'/': tree_path = fs_path_bytes.replace(os_sep_bytes, b'/') else: tree_path = fs_path_bytes return tree_path def index_entry_from_path(path, object_store=None): """Create an index from a filesystem path. This returns an index value for files, symlinks and tree references. for directories and non-existant files it returns None Args: path: Path to create an index entry for object_store: Optional object store to save new blobs in Returns: An index entry; None for directories """ assert isinstance(path, bytes) st = os.lstat(path) if stat.S_ISDIR(st.st_mode): if os.path.exists(os.path.join(path, b'.git')): head = read_submodule_head(path) if head is None: return None return index_entry_from_stat( st, head, 0, mode=S_IFGITLINK) return None if stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode): blob = blob_from_path_and_stat(path, st) if object_store is not None: object_store.add_object(blob) return index_entry_from_stat(st, blob.id, 0) return None def iter_fresh_entries(paths, root_path, object_store=None): """Iterate over current versions of index entries on disk. Args: paths: Paths to iterate over root_path: Root path to access from store: Optional store to save new blobs in Returns: Iterator over path, index_entry """ for path in paths: p = _tree_to_fs_path(root_path, path) try: entry = index_entry_from_path(p, object_store=object_store) except EnvironmentError as e: if e.errno in (errno.ENOENT, errno.EISDIR): entry = None else: raise yield path, entry def iter_fresh_blobs(index, root_path): """Iterate over versions of blobs on disk referenced by index. Don't use this function; it removes missing entries from index. Args: index: Index file root_path: Root path to access from include_deleted: Include deleted entries with sha and mode set to None Returns: Iterator over path, sha, mode """ import warnings warnings.warn(PendingDeprecationWarning, "Use iter_fresh_objects instead.") for entry in iter_fresh_objects( index, root_path, include_deleted=True): if entry[1] is None: del index[entry[0]] else: yield entry def iter_fresh_objects(paths, root_path, include_deleted=False, object_store=None): """Iterate over versions of objecs on disk referenced by index. Args: index: Index file root_path: Root path to access from include_deleted: Include deleted entries with sha and mode set to None object_store: Optional object store to report new items to Returns: Iterator over path, sha, mode """ for path, entry in iter_fresh_entries(paths, root_path, object_store=object_store): if entry is None: if include_deleted: yield path, None, None else: entry = IndexEntry(*entry) yield path, entry.sha, cleanup_mode(entry.mode) def refresh_index(index, root_path): """Refresh the contents of an index. This is the equivalent to running 'git commit -a'. Args: index: Index to update root_path: Root filesystem path """ for path, entry in iter_fresh_entries(index, root_path): index[path] = path diff --git a/dulwich/object_store.py b/dulwich/object_store.py index a0b54fc8..f77547a5 100644 --- a/dulwich/object_store.py +++ b/dulwich/object_store.py @@ -1,1428 +1,1427 @@ # object_store.py -- Object store for git objects # Copyright (C) 2008-2013 Jelmer Vernooij # and others # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Git object store interfaces and implementation.""" from io import BytesIO import errno import os import stat import sys import tempfile from dulwich.diff_tree import ( tree_changes, walk_trees, ) from dulwich.errors import ( NotTreeError, ) from dulwich.file import GitFile from dulwich.objects import ( Commit, ShaFile, Tag, Tree, ZERO_SHA, hex_to_sha, sha_to_hex, hex_to_filename, S_ISGITLINK, object_class, ) from dulwich.pack import ( Pack, PackData, PackInflater, PackFileDisappeared, iter_sha1, pack_objects_to_data, write_pack_header, write_pack_index_v2, write_pack_data, write_pack_object, compute_file_sha, PackIndexer, PackStreamCopier, ) from dulwich.refs import ANNOTATED_TAG_SUFFIX INFODIR = 'info' PACKDIR = 'pack' class BaseObjectStore(object): """Object store interface.""" def determine_wants_all(self, refs): return [sha for (ref, sha) in refs.items() if sha not in self and not ref.endswith(ANNOTATED_TAG_SUFFIX) and not sha == ZERO_SHA] def iter_shas(self, shas): """Iterate over the objects for the specified shas. Args: shas: Iterable object with SHAs Returns: Object iterator """ return ObjectStoreIterator(self, shas) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" raise NotImplementedError(self.contains_loose) def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" raise NotImplementedError(self.contains_packed) def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ return self.contains_packed(sha) or self.contains_loose(sha) @property def packs(self): """Iterable of pack objects.""" raise NotImplementedError def get_raw(self, name): """Obtain the raw text for an object. Args: name: sha for the object. Returns: tuple with numeric type and object contents. """ raise NotImplementedError(self.get_raw) def __getitem__(self, sha): """Obtain an object by SHA1.""" type_num, uncomp = self.get_raw(sha) return ShaFile.from_raw_string(type_num, uncomp, sha=sha) def __iter__(self): """Iterate over the SHAs that are present in this store.""" raise NotImplementedError(self.__iter__) def add_object(self, obj): """Add a single object to this object store. """ raise NotImplementedError(self.add_object) def add_objects(self, objects, progress=None): """Add a set of objects to this object store. Args: objects: Iterable over a list of (object, path) tuples """ raise NotImplementedError(self.add_objects) def add_pack_data(self, count, pack_data, progress=None): """Add pack data to this object store. Args: num_items: Number of items to add pack_data: Iterator over pack data tuples """ if count == 0: # Don't bother writing an empty pack file return f, commit, abort = self.add_pack() try: write_pack_data( f, count, pack_data, progress, compression_level=self.pack_compression_level) except BaseException: abort() raise else: return commit() def tree_changes(self, source, target, want_unchanged=False, include_trees=False, change_type_same=False, rename_detector=None): """Find the differences between the contents of two trees Args: source: SHA1 of the source tree target: SHA1 of the target tree want_unchanged: Whether unchanged files should be reported include_trees: Whether to include trees change_type_same: Whether to report files changing type in the same entry. Returns: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ for change in tree_changes(self, source, target, want_unchanged=want_unchanged, include_trees=include_trees, change_type_same=change_type_same, rename_detector=rename_detector): yield ((change.old.path, change.new.path), (change.old.mode, change.new.mode), (change.old.sha, change.new.sha)) def iter_tree_contents(self, tree_id, include_trees=False): """Iterate the contents of a tree and all subtrees. Iteration is depth-first pre-order, as in e.g. os.walk. Args: tree_id: SHA1 of the tree. include_trees: If True, include tree objects in the iteration. Returns: Iterator over TreeEntry namedtuples for all the objects in a tree. """ for entry, _ in walk_trees(self, tree_id, None): if ((entry.mode is not None and not stat.S_ISDIR(entry.mode)) or include_trees): yield entry def find_missing_objects(self, haves, wants, shallow=None, progress=None, get_tagged=None, get_parents=lambda commit: commit.parents, depth=None): """Find the missing objects required for a set of revisions. Args: haves: Iterable over SHAs already in common. wants: Iterable over SHAs of objects to fetch. shallow: Set of shallow commit SHA1s to skip progress: Simple progress function that will be called with updated progress strings. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. get_parents: Optional function for getting the parents of a commit. Returns: Iterator over (sha, path) pairs. """ finder = MissingObjectFinder(self, haves, wants, shallow, progress, get_tagged, get_parents=get_parents) return iter(finder.next, None) def find_common_revisions(self, graphwalker): """Find which revisions this store has in common using graphwalker. Args: graphwalker: A graphwalker object. Returns: List of SHAs that are in common """ haves = [] sha = next(graphwalker) while sha: if sha in self: haves.append(sha) graphwalker.ack(sha) sha = next(graphwalker) return haves def generate_pack_contents(self, have, want, shallow=None, progress=None): """Iterate over the contents of a pack file. Args: have: List of SHA1s of objects that should not be sent want: List of SHA1s of objects that should be sent shallow: Set of shallow commit SHA1s to skip progress: Optional progress reporting method """ missing = self.find_missing_objects(have, want, shallow, progress) return self.iter_shas(missing) def generate_pack_data(self, have, want, shallow=None, progress=None, ofs_delta=True): """Generate pack data objects for a set of wants/haves. Args: have: List of SHA1s of objects that should not be sent want: List of SHA1s of objects that should be sent shallow: Set of shallow commit SHA1s to skip ofs_delta: Whether OFS deltas can be included progress: Optional progress reporting method """ # TODO(jelmer): More efficient implementation return pack_objects_to_data( self.generate_pack_contents(have, want, shallow, progress)) def peel_sha(self, sha): """Peel all tags from a SHA. Args: sha: The object SHA to peel. Returns: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ obj = self[sha] obj_class = object_class(obj.type_name) while obj_class is Tag: obj_class, sha = obj.object obj = self[sha] return obj def _collect_ancestors(self, heads, common=set(), shallow=set(), get_parents=lambda commit: commit.parents): """Collect all ancestors of heads up to (excluding) those in common. Args: heads: commits to start from common: commits to end at, or empty set to walk repository completely get_parents: Optional function for getting the parents of a commit. Returns: a tuple (A, B) where A - all commits reachable from heads but not present in common, B - common (shared) elements that are directly reachable from heads """ bases = set() commits = set() queue = [] queue.extend(heads) while queue: e = queue.pop(0) if e in common: bases.add(e) elif e not in commits: commits.add(e) if e in shallow: continue cmt = self[e] queue.extend(get_parents(cmt)) return (commits, bases) def close(self): """Close any files opened by this object store.""" # Default implementation is a NO-OP class PackBasedObjectStore(BaseObjectStore): def __init__(self, pack_compression_level=-1): self._pack_cache = {} self.pack_compression_level = pack_compression_level @property def alternates(self): return [] def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed. This does not check alternates. """ for pack in self.packs: try: if sha in pack: return True except PackFileDisappeared: pass return False def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ if self.contains_packed(sha) or self.contains_loose(sha): return True for alternate in self.alternates: if sha in alternate: return True return False def _add_cached_pack(self, base_name, pack): """Add a newly appeared pack to the cache by path. """ prev_pack = self._pack_cache.get(base_name) if prev_pack is not pack: self._pack_cache[base_name] = pack if prev_pack: prev_pack.close() def _clear_cached_packs(self): pack_cache = self._pack_cache self._pack_cache = {} while pack_cache: (name, pack) = pack_cache.popitem() pack.close() def _iter_cached_packs(self): return self._pack_cache.values() def _update_pack_cache(self): raise NotImplementedError(self._update_pack_cache) def close(self): self._clear_cached_packs() @property def packs(self): """List with pack objects.""" return ( list(self._iter_cached_packs()) + list(self._update_pack_cache())) def _iter_alternate_objects(self): """Iterate over the SHAs of all the objects in alternate stores.""" for alternate in self.alternates: for alternate_object in alternate: yield alternate_object def _iter_loose_objects(self): """Iterate over the SHAs of all loose objects.""" raise NotImplementedError(self._iter_loose_objects) def _get_loose_object(self, sha): raise NotImplementedError(self._get_loose_object) def _remove_loose_object(self, sha): raise NotImplementedError(self._remove_loose_object) def _remove_pack(self, name): raise NotImplementedError(self._remove_pack) def pack_loose_objects(self): """Pack loose objects. Returns: Number of objects packed """ objects = set() for sha in self._iter_loose_objects(): objects.add((self._get_loose_object(sha), None)) self.add_objects(list(objects)) for obj, path in objects: self._remove_loose_object(obj.id) return len(objects) def repack(self): """Repack the packs in this repository. Note that this implementation is fairly naive and currently keeps all objects in memory while it repacks. """ loose_objects = set() for sha in self._iter_loose_objects(): loose_objects.add(self._get_loose_object(sha)) objects = {(obj, None) for obj in loose_objects} old_packs = {p.name(): p for p in self.packs} for name, pack in old_packs.items(): objects.update((obj, None) for obj in pack.iterobjects()) # The name of the consolidated pack might match the name of a # pre-existing pack. Take care not to remove the newly created # consolidated pack. consolidated = self.add_objects(objects) old_packs.pop(consolidated.name(), None) for obj in loose_objects: self._remove_loose_object(obj.id) for name, pack in old_packs.items(): self._remove_pack(pack) self._update_pack_cache() return len(objects) def __iter__(self): """Iterate over the SHAs that are present in this store.""" self._update_pack_cache() for pack in self._iter_cached_packs(): try: for sha in pack: yield sha except PackFileDisappeared: pass for sha in self._iter_loose_objects(): yield sha for sha in self._iter_alternate_objects(): yield sha def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose. This does not check alternates. """ return self._get_loose_object(sha) is not None def get_raw(self, name): """Obtain the raw fulltext for an object. Args: name: sha for the object. Returns: tuple with numeric type and object contents. """ if name == ZERO_SHA: raise KeyError(name) if len(name) == 40: sha = hex_to_sha(name) hexsha = name elif len(name) == 20: sha = name hexsha = None else: raise AssertionError("Invalid object name %r" % (name, )) for pack in self._iter_cached_packs(): try: return pack.get_raw(sha) except (KeyError, PackFileDisappeared): pass if hexsha is None: hexsha = sha_to_hex(name) ret = self._get_loose_object(hexsha) if ret is not None: return ret.type_num, ret.as_raw_string() # Maybe something else has added a pack with the object # in the mean time? for pack in self._update_pack_cache(): try: return pack.get_raw(sha) except KeyError: pass for alternate in self.alternates: try: return alternate.get_raw(hexsha) except KeyError: pass raise KeyError(hexsha) def add_objects(self, objects, progress=None): """Add a set of objects to this object store. Args: objects: Iterable over (object, path) tuples, should support __len__. Returns: Pack object of the objects written. """ return self.add_pack_data( *pack_objects_to_data(objects), progress=progress) class DiskObjectStore(PackBasedObjectStore): """Git-style object store that exists on disk.""" def __init__(self, path, loose_compression_level=-1, pack_compression_level=-1): """Open an object store. Args: path: Path of the object store. loose_compression_level: zlib compression level for loose objects pack_compression_level: zlib compression level for pack objects """ super(DiskObjectStore, self).__init__( pack_compression_level=pack_compression_level) self.path = path self.pack_dir = os.path.join(self.path, PACKDIR) self._alternates = None self.loose_compression_level = loose_compression_level self.pack_compression_level = pack_compression_level def __repr__(self): return "<%s(%r)>" % (self.__class__.__name__, self.path) @classmethod def from_config(cls, path, config): try: default_compression_level = int(config.get( (b'core', ), b'compression').decode()) except KeyError: default_compression_level = -1 try: loose_compression_level = int(config.get( (b'core', ), b'looseCompression').decode()) except KeyError: loose_compression_level = default_compression_level try: pack_compression_level = int(config.get( (b'core', ), 'packCompression').decode()) except KeyError: pack_compression_level = default_compression_level return cls(path, loose_compression_level, pack_compression_level) @property def alternates(self): if self._alternates is not None: return self._alternates self._alternates = [] for path in self._read_alternate_paths(): self._alternates.append(DiskObjectStore(path)) return self._alternates def _read_alternate_paths(self): try: f = GitFile(os.path.join(self.path, INFODIR, "alternates"), 'rb') except (OSError, IOError) as e: if e.errno == errno.ENOENT: return raise with f: for line in f.readlines(): line = line.rstrip(b"\n") if line[0] == b"#": continue if os.path.isabs(line): - yield line.decode(sys.getfilesystemencoding()) + yield os.fsdecode(line) else: - yield os.path.join(self.path, line).decode( - sys.getfilesystemencoding()) + yield os.fsdecode(os.path.join(self.path, line)) def add_alternate_path(self, path): """Add an alternate path to this object store. """ try: os.mkdir(os.path.join(self.path, INFODIR)) except OSError as e: if e.errno != errno.EEXIST: raise alternates_path = os.path.join(self.path, INFODIR, "alternates") with GitFile(alternates_path, 'wb') as f: try: orig_f = open(alternates_path, 'rb') except (OSError, IOError) as e: if e.errno != errno.ENOENT: raise else: with orig_f: f.write(orig_f.read()) - f.write(path.encode(sys.getfilesystemencoding()) + b"\n") + f.write(os.fsencode(path) + b"\n") if not os.path.isabs(path): path = os.path.join(self.path, path) self.alternates.append(DiskObjectStore(path)) def _update_pack_cache(self): """Read and iterate over new pack files and cache them.""" try: pack_dir_contents = os.listdir(self.pack_dir) except OSError as e: if e.errno == errno.ENOENT: self.close() return [] raise pack_files = set() for name in pack_dir_contents: if name.startswith("pack-") and name.endswith(".pack"): # verify that idx exists first (otherwise the pack was not yet # fully written) idx_name = os.path.splitext(name)[0] + ".idx" if idx_name in pack_dir_contents: pack_name = name[:-len(".pack")] pack_files.add(pack_name) # Open newly appeared pack files new_packs = [] for f in pack_files: if f not in self._pack_cache: pack = Pack(os.path.join(self.pack_dir, f)) new_packs.append(pack) self._pack_cache[f] = pack # Remove disappeared pack files for f in set(self._pack_cache) - pack_files: self._pack_cache.pop(f).close() return new_packs def _get_shafile_path(self, sha): # Check from object dir return hex_to_filename(self.path, sha) def _iter_loose_objects(self): for base in os.listdir(self.path): if len(base) != 2: continue for rest in os.listdir(os.path.join(self.path, base)): - yield (base+rest).encode(sys.getfilesystemencoding()) + yield os.fsencode(base+rest) def _get_loose_object(self, sha): path = self._get_shafile_path(sha) try: return ShaFile.from_path(path) except (OSError, IOError) as e: if e.errno == errno.ENOENT: return None raise def _remove_loose_object(self, sha): os.remove(self._get_shafile_path(sha)) def _remove_pack(self, pack): try: del self._pack_cache[os.path.basename(pack._basename)] except KeyError: pass pack.close() os.remove(pack.data.path) os.remove(pack.index.path) def _get_pack_basepath(self, entries): suffix = iter_sha1(entry[0] for entry in entries) # TODO: Handle self.pack_dir being bytes suffix = suffix.decode('ascii') return os.path.join(self.pack_dir, "pack-" + suffix) def _complete_thin_pack(self, f, path, copier, indexer): """Move a specific file containing a pack into the pack directory. Note: The file should be on the same file system as the packs directory. Args: f: Open file object for the pack. path: Path to the pack file. copier: A PackStreamCopier to use for writing pack data. indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Must flush before reading (http://bugs.python.org/issue3207) f.flush() # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Must reposition before writing (http://bugs.python.org/issue3207) f.seek(0, os.SEEK_CUR) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) offset = f.tell() crc32 = write_pack_object( f, type_num, data, sha=new_sha, compression_level=self.pack_compression_level) entries.append((ext_sha, offset, crc32)) pack_sha = new_sha.digest() f.write(pack_sha) f.close() # Move the pack in. entries.sort() pack_base_name = self._get_pack_basepath(entries) target_pack = pack_base_name + '.pack' if sys.platform == 'win32': # Windows might have the target pack file lingering. Attempt # removal, silently passing if the target does not exist. try: os.remove(target_pack) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise os.rename(path, target_pack) # Write the index. index_file = GitFile(pack_base_name + '.idx', 'wb') try: write_pack_index_v2(index_file, entries, pack_sha) index_file.close() finally: index_file.abort() # Add the pack to the store and return it. final_pack = Pack(pack_base_name) final_pack.check_length_and_checksum() self._add_cached_pack(pack_base_name, final_pack) return final_pack def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. They should never be placed in the object store directly, and always indexed and completed as they are copied. Args: read_all: Read function that blocks until the number of requested bytes are read. read_some: Read function that returns at least one byte, but may not return the number of bytes requested. Returns: A Pack object pointing at the now-completed thin pack in the objects/pack directory. """ fd, path = tempfile.mkstemp(dir=self.path, prefix='tmp_pack_') with os.fdopen(fd, 'w+b') as f: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() return self._complete_thin_pack(f, path, copier, indexer) def move_in_pack(self, path): """Move a specific file containing a pack into the pack directory. Note: The file should be on the same file system as the packs directory. Args: path: Path to the pack file. """ with PackData(path) as p: entries = p.sorted_entries() basename = self._get_pack_basepath(entries) index_name = basename + ".idx" if not os.path.exists(index_name): with GitFile(index_name, "wb") as f: write_pack_index_v2(f, entries, p.get_stored_checksum()) for pack in self.packs: if pack._basename == basename: return pack target_pack = basename + '.pack' if sys.platform == 'win32': # Windows might have the target pack file lingering. Attempt # removal, silently passing if the target does not exist. try: os.remove(target_pack) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise os.rename(path, target_pack) final_pack = Pack(basename) self._add_cached_pack(basename, final_pack) return final_pack def add_pack(self): """Add a new pack to this object store. Returns: Fileobject to write to, a commit function to call when the pack is finished and an abort function. """ fd, path = tempfile.mkstemp(dir=self.pack_dir, suffix=".pack") f = os.fdopen(fd, 'wb') def commit(): f.flush() os.fsync(fd) f.close() if os.path.getsize(path) > 0: return self.move_in_pack(path) else: os.remove(path) return None def abort(): f.close() os.remove(path) return f, commit, abort def add_object(self, obj): """Add a single object to this object store. Args: obj: Object to add """ path = self._get_shafile_path(obj.id) dir = os.path.dirname(path) try: os.mkdir(dir) except OSError as e: if e.errno != errno.EEXIST: raise if os.path.exists(path): return # Already there, no need to write again with GitFile(path, 'wb') as f: f.write(obj.as_legacy_object( compression_level=self.loose_compression_level)) @classmethod def init(cls, path): try: os.mkdir(path) except OSError as e: if e.errno != errno.EEXIST: raise os.mkdir(os.path.join(path, "info")) os.mkdir(os.path.join(path, PACKDIR)) return cls(path) class MemoryObjectStore(BaseObjectStore): """Object store that keeps all objects in memory.""" def __init__(self): super(MemoryObjectStore, self).__init__() self._data = {} self.pack_compression_level = -1 def _to_hexsha(self, sha): if len(sha) == 40: return sha elif len(sha) == 20: return sha_to_hex(sha) else: raise ValueError("Invalid sha %r" % (sha,)) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" return self._to_hexsha(sha) in self._data def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" return False def __iter__(self): """Iterate over the SHAs that are present in this store.""" return iter(self._data.keys()) @property def packs(self): """List with pack objects.""" return [] def get_raw(self, name): """Obtain the raw text for an object. Args: name: sha for the object. Returns: tuple with numeric type and object contents. """ obj = self[self._to_hexsha(name)] return obj.type_num, obj.as_raw_string() def __getitem__(self, name): return self._data[self._to_hexsha(name)].copy() def __delitem__(self, name): """Delete an object from this store, for testing only.""" del self._data[self._to_hexsha(name)] def add_object(self, obj): """Add a single object to this object store. """ self._data[obj.id] = obj.copy() def add_objects(self, objects, progress=None): """Add a set of objects to this object store. Args: objects: Iterable over a list of (object, path) tuples """ for obj, path in objects: self.add_object(obj) def add_pack(self): """Add a new pack to this object store. Because this object store doesn't support packs, we extract and add the individual objects. Returns: Fileobject to write to and a commit function to call when the pack is finished. """ f = BytesIO() def commit(): p = PackData.from_file(BytesIO(f.getvalue()), f.tell()) f.close() for obj in PackInflater.for_pack_data(p, self.get_raw): self.add_object(obj) def abort(): pass return f, commit, abort def _complete_thin_pack(self, f, indexer): """Complete a thin pack by adding external references. Args: f: Open file object for the pack. indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) write_pack_object( f, type_num, data, sha=new_sha) pack_sha = new_sha.digest() f.write(pack_sha) def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. Because this object store doesn't support packs, we extract and add the individual objects. Args: read_all: Read function that blocks until the number of requested bytes are read. read_some: Read function that returns at least one byte, but may not return the number of bytes requested. """ f, commit, abort = self.add_pack() try: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() self._complete_thin_pack(f, indexer) except BaseException: abort() raise else: commit() class ObjectIterator(object): """Interface for iterating over objects.""" def iterobjects(self): raise NotImplementedError(self.iterobjects) class ObjectStoreIterator(ObjectIterator): """ObjectIterator that works on top of an ObjectStore.""" def __init__(self, store, sha_iter): """Create a new ObjectIterator. Args: store: Object store to retrieve from sha_iter: Iterator over (sha, path) tuples """ self.store = store self.sha_iter = sha_iter self._shas = [] def __iter__(self): """Yield tuple with next object and path.""" for sha, path in self.itershas(): yield self.store[sha], path def iterobjects(self): """Iterate over just the objects.""" for o, path in self: yield o def itershas(self): """Iterate over the SHAs.""" for sha in self._shas: yield sha for sha in self.sha_iter: self._shas.append(sha) yield sha def __contains__(self, needle): """Check if an object is present. Note: This checks if the object is present in the underlying object store, not if it would be yielded by the iterator. Args: needle: SHA1 of the object to check for """ if needle == ZERO_SHA: return False return needle in self.store def __getitem__(self, key): """Find an object by SHA1. Note: This retrieves the object from the underlying object store. It will also succeed if the object would not be returned by the iterator. """ return self.store[key] def __len__(self): """Return the number of objects.""" return len(list(self.itershas())) def empty(self): import warnings warnings.warn('Use bool() instead.', DeprecationWarning) return self._empty() def _empty(self): it = self.itershas() try: next(it) except StopIteration: return True else: return False def __bool__(self): """Indicate whether this object has contents.""" return not self._empty() def tree_lookup_path(lookup_obj, root_sha, path): """Look up an object in a Git tree. Args: lookup_obj: Callback for retrieving object by SHA1 root_sha: SHA1 of the root tree path: Path to lookup Returns: A tuple of (mode, SHA) of the resulting path. """ tree = lookup_obj(root_sha) if not isinstance(tree, Tree): raise NotTreeError(root_sha) return tree.lookup_path(lookup_obj, path) def _collect_filetree_revs(obj_store, tree_sha, kset): """Collect SHA1s of files and directories for specified tree. Args: obj_store: Object store to get objects by SHA from tree_sha: tree reference to walk kset: set to fill with references to files and directories """ filetree = obj_store[tree_sha] for name, mode, sha in filetree.iteritems(): if not S_ISGITLINK(mode) and sha not in kset: kset.add(sha) if stat.S_ISDIR(mode): _collect_filetree_revs(obj_store, sha, kset) def _split_commits_and_tags(obj_store, lst, ignore_unknown=False): """Split object id list into three lists with commit, tag, and other SHAs. Commits referenced by tags are included into commits list as well. Only SHA1s known in this repository will get through, and unless ignore_unknown argument is True, KeyError is thrown for SHA1 missing in the repository Args: obj_store: Object store to get objects by SHA1 from lst: Collection of commit and tag SHAs ignore_unknown: True to skip SHA1 missing in the repository silently. Returns: A tuple of (commits, tags, others) SHA1s """ commits = set() tags = set() others = set() for e in lst: try: o = obj_store[e] except KeyError: if not ignore_unknown: raise else: if isinstance(o, Commit): commits.add(e) elif isinstance(o, Tag): tags.add(e) tagged = o.object[1] c, t, o = _split_commits_and_tags( obj_store, [tagged], ignore_unknown=ignore_unknown) commits |= c tags |= t others |= o else: others.add(e) return (commits, tags, others) class MissingObjectFinder(object): """Find the objects missing from another object store. Args: object_store: Object store containing at least all objects to be sent haves: SHA1s of commits not to send (already present in target) wants: SHA1s of commits to send progress: Optional function to report progress to. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. get_parents: Optional function for getting the parents of a commit. tagged: dict of pointed-to sha -> tag sha for including tags """ def __init__(self, object_store, haves, wants, shallow=None, progress=None, get_tagged=None, get_parents=lambda commit: commit.parents): self.object_store = object_store if shallow is None: shallow = set() self._get_parents = get_parents # process Commits and Tags differently # Note, while haves may list commits/tags not available locally, # and such SHAs would get filtered out by _split_commits_and_tags, # wants shall list only known SHAs, and otherwise # _split_commits_and_tags fails with KeyError have_commits, have_tags, have_others = ( _split_commits_and_tags(object_store, haves, True)) want_commits, want_tags, want_others = ( _split_commits_and_tags(object_store, wants, False)) # all_ancestors is a set of commits that shall not be sent # (complete repository up to 'haves') all_ancestors = object_store._collect_ancestors( have_commits, shallow=shallow, get_parents=self._get_parents)[0] # all_missing - complete set of commits between haves and wants # common - commits from all_ancestors we hit into while # traversing parent hierarchy of wants missing_commits, common_commits = object_store._collect_ancestors( want_commits, all_ancestors, shallow=shallow, get_parents=self._get_parents) self.sha_done = set() # Now, fill sha_done with commits and revisions of # files and directories known to be both locally # and on target. Thus these commits and files # won't get selected for fetch for h in common_commits: self.sha_done.add(h) cmt = object_store[h] _collect_filetree_revs(object_store, cmt.tree, self.sha_done) # record tags we have as visited, too for t in have_tags: self.sha_done.add(t) missing_tags = want_tags.difference(have_tags) missing_others = want_others.difference(have_others) # in fact, what we 'want' is commits, tags, and others # we've found missing wants = missing_commits.union(missing_tags) wants = wants.union(missing_others) self.objects_to_send = set([(w, None, False) for w in wants]) if progress is None: self.progress = lambda x: None else: self.progress = progress self._tagged = get_tagged and get_tagged() or {} def add_todo(self, entries): self.objects_to_send.update([e for e in entries if not e[0] in self.sha_done]) def next(self): while True: if not self.objects_to_send: return None (sha, name, leaf) = self.objects_to_send.pop() if sha not in self.sha_done: break if not leaf: o = self.object_store[sha] if isinstance(o, Commit): self.add_todo([(o.tree, "", False)]) elif isinstance(o, Tree): self.add_todo([(s, n, not stat.S_ISDIR(m)) for n, m, s in o.iteritems() if not S_ISGITLINK(m)]) elif isinstance(o, Tag): self.add_todo([(o.object[1], None, False)]) if sha in self._tagged: self.add_todo([(self._tagged[sha], None, True)]) self.sha_done.add(sha) self.progress(("counting objects: %d\r" % len(self.sha_done)).encode('ascii')) return (sha, name) __next__ = next class ObjectStoreGraphWalker(object): """Graph walker that finds what commits are missing from an object store. :ivar heads: Revisions without descendants in the local repo :ivar get_parents: Function to retrieve parents in the local repo """ def __init__(self, local_heads, get_parents, shallow=None): """Create a new instance. Args: local_heads: Heads to start search with get_parents: Function for finding the parents of a SHA1. """ self.heads = set(local_heads) self.get_parents = get_parents self.parents = {} if shallow is None: shallow = set() self.shallow = shallow def ack(self, sha): """Ack that a revision and its ancestors are present in the source.""" if len(sha) != 40: raise ValueError("unexpected sha %r received" % sha) ancestors = set([sha]) # stop if we run out of heads to remove while self.heads: for a in ancestors: if a in self.heads: self.heads.remove(a) # collect all ancestors new_ancestors = set() for a in ancestors: ps = self.parents.get(a) if ps is not None: new_ancestors.update(ps) self.parents[a] = None # no more ancestors; stop if not new_ancestors: break ancestors = new_ancestors def next(self): """Iterate over ancestors of heads in the target.""" if self.heads: ret = self.heads.pop() ps = self.get_parents(ret) self.parents[ret] = ps self.heads.update( [p for p in ps if p not in self.parents]) return ret return None __next__ = next def commit_tree_changes(object_store, tree, changes): """Commit a specified set of changes to a tree structure. This will apply a set of changes on top of an existing tree, storing new objects in object_store. changes are a list of tuples with (path, mode, object_sha). Paths can be both blobs and trees. See the mode and object sha to None deletes the path. This method works especially well if there are only a small number of changes to a big tree. For a large number of changes to a large tree, use e.g. commit_tree. Args: object_store: Object store to store new objects in and retrieve old ones from. tree: Original tree root changes: changes to apply Returns: New tree root object """ # TODO(jelmer): Save up the objects and add them using .add_objects # rather than with individual calls to .add_object. nested_changes = {} for (path, new_mode, new_sha) in changes: try: (dirname, subpath) = path.split(b'/', 1) except ValueError: if new_sha is None: del tree[path] else: tree[path] = (new_mode, new_sha) else: nested_changes.setdefault(dirname, []).append( (subpath, new_mode, new_sha)) for name, subchanges in nested_changes.items(): try: orig_subtree = object_store[tree[name][1]] except KeyError: orig_subtree = Tree() subtree = commit_tree_changes(object_store, orig_subtree, subchanges) if len(subtree) == 0: del tree[name] else: tree[name] = (stat.S_IFDIR, subtree.id) object_store.add_object(tree) return tree class OverlayObjectStore(BaseObjectStore): """Object store that can overlay multiple object stores.""" def __init__(self, bases, add_store=None): self.bases = bases self.add_store = add_store def add_object(self, object): if self.add_store is None: raise NotImplementedError(self.add_object) return self.add_store.add_object(object) def add_objects(self, objects, progress=None): if self.add_store is None: raise NotImplementedError(self.add_object) return self.add_store.add_objects(objects, progress) @property def packs(self): ret = [] for b in self.bases: ret.extend(b.packs) return ret def __iter__(self): done = set() for b in self.bases: for o_id in b: if o_id not in done: yield o_id done.add(o_id) def get_raw(self, sha_id): for b in self.bases: try: return b.get_raw(sha_id) except KeyError: pass raise KeyError(sha_id) def contains_packed(self, sha): for b in self.bases: if b.contains_packed(sha): return True return False def contains_loose(self, sha): for b in self.bases: if b.contains_loose(sha): return True return False def read_packs_file(f): """Yield the packs listed in a packs file.""" for line in f.read().splitlines(): if not line: continue (kind, name) = line.split(b" ", 1) if kind != b"P": continue - yield name.decode(sys.getfilesystemencoding()) + yield os.fsdecode(name) diff --git a/dulwich/porcelain.py b/dulwich/porcelain.py index 7e88e61e..443083b6 100644 --- a/dulwich/porcelain.py +++ b/dulwich/porcelain.py @@ -1,1615 +1,1615 @@ # 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} * check-ignore * checkout * clone * commit * commit-tree * daemon * describe * diff-tree * fetch * init * ls-files * ls-remote * ls-tree * pull * push * rm * remote{_add} * 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. Functions should generally accept both unicode strings and bytestrings """ from collections import namedtuple from contextlib import ( closing, contextmanager, ) from io import BytesIO, RawIOBase import datetime import os import posixpath import shutil import stat import sys import time from dulwich.archive import ( tar_stream, ) from dulwich.client import ( get_transport_and_path, ) from dulwich.config import ( StackedConfig, ) 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.ignore import IgnoreFilterManager from dulwich.index import ( blob_from_path_and_stat, get_unstaged_changes, ) from dulwich.object_store import ( tree_lookup_path, ) from dulwich.objects import ( Commit, Tag, format_timezone, parse_timezone, pretty_format_tree_entry, ) from dulwich.objectspec import ( parse_commit, parse_object, parse_ref, parse_reftuples, parse_tree, ) 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, LOCAL_BRANCH_PREFIX, strip_peeled_refs, ) 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') class NoneStream(RawIOBase): """Fallback if stdout or stderr are unavailable, does nothing.""" def read(self, size=-1): return None def readall(self): return None def readinto(self, b): return None def write(self, b): return None default_bytes_out_stream = ( getattr(sys.stdout, 'buffer', None) or NoneStream()) default_bytes_err_stream = ( getattr(sys.stderr, 'buffer', None) or NoneStream()) DEFAULT_ENCODING = 'utf-8' class RemoteExists(Exception): """Raised when the remote already exists.""" 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 path_to_tree_path(repopath, path): """Convert a path to a path usable in an index, e.g. bytes and relative to the repository root. Args: repopath: Repository path, absolute or relative to the cwd path: A path, absolute or relative to the cwd Returns: A path formatted for use in e.g. an index """ if not isinstance(path, bytes): - path = path.encode(sys.getfilesystemencoding()) + path = os.fsencode(path) if not isinstance(repopath, bytes): - repopath = repopath.encode(sys.getfilesystemencoding()) + repopath = os.fsencode(repopath) treepath = os.path.relpath(path, repopath) if treepath.startswith(b'..'): raise ValueError('Path not in repo') if os.path.sep != '/': treepath = treepath.replace(os.path.sep.encode('ascii'), b'/') return treepath def archive(repo, committish=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream): """Create an archive. Args: repo: Path of repository for which to generate an archive. committish: Commit SHA1 or ref to use outstream: Output stream (defaults to stdout) errstream: Error stream (defaults to stderr) """ if committish is None: committish = "HEAD" with open_repo_closing(repo) as repo_obj: c = parse_commit(repo_obj, committish) 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. Args: 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. Args: repo: path to the repository ref_name: short name of the new ref force: force settings without checking if it exists in refs/heads """ with open_repo_closing(repo) as repo_obj: ref_path = _make_branch_ref(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, encoding=None): """Create a new commit. Args: repo: Path to repository message: Optional commit message author: Optional author name and email committer: Optional committer name and email Returns: SHA1 of the new commit """ # FIXME: Support --all argument # FIXME: Support --signoff argument if getattr(message, 'encode', None): message = message.encode(encoding or DEFAULT_ENCODING) if getattr(author, 'encode', None): author = author.encode(encoding or DEFAULT_ENCODING) if getattr(committer, 'encode', None): committer = committer.encode(encoding or DEFAULT_ENCODING) with open_repo_closing(repo) as r: return r.do_commit( message=message, author=author, committer=committer, encoding=encoding) def commit_tree(repo, tree, message=None, author=None, committer=None): """Create a new commit object. Args: repo: Path to repository tree: An existing tree object author: Optional author name and email 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. Args: path: Path to repository. bare: Whether to create a bare repository. Returns: 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", depth=None, **kwargs): """Clone a local or remote git repository. Args: source: Path or URL for source repository target: Path to target repository (optional) bare: Whether or not to create a bare repository checkout: Whether or not to check-out HEAD after cloning errstream: Optional stream to write progress to outstream: Optional stream to write progress to (deprecated) origin: Name of remote from the repository used to clone depth: Depth to fetch at Returns: The new repository """ # TODO(jelmer): This code overlaps quite a bit with Repo.clone 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") if target is None: target = source.split("/")[-1] if not os.path.exists(target): os.mkdir(target) if bare: r = Repo.init_bare(target) else: r = Repo.init(target) reflog_message = b'clone: from ' + source.encode('utf-8') try: fetch_result = fetch( r, source, origin, errstream=errstream, message=reflog_message, depth=depth, **kwargs) target_config = r.get_config() if not isinstance(source, bytes): source = source.encode(DEFAULT_ENCODING) target_config.set((b'remote', origin), b'url', source) target_config.set( (b'remote', origin), b'fetch', b'+refs/heads/*:refs/remotes/' + origin + b'/*') target_config.write_to_path() # TODO(jelmer): Support symref capability, # https://github.com/jelmer/dulwich/issues/485 try: head = r[fetch_result[b'HEAD']] except KeyError: head = None else: r[b'HEAD'] = head.id if checkout and not bare and head is not None: errstream.write(b'Checking out ' + head.id + b'\n') r.reset_index(head.tree) except BaseException: shutil.rmtree(target) r.close() raise return r def add(repo=".", paths=None): """Add files to the staging area. Args: repo: Repository for the files paths: Paths to add. No value passed stages all modified files. Returns: Tuple with set of added files and ignored files """ ignored = set() with open_repo_closing(repo) as r: ignore_manager = IgnoreFilterManager.from_repo(r) if not paths: paths = list( get_untracked_paths(os.getcwd(), r.path, r.open_index())) relpaths = [] if not isinstance(paths, list): paths = [paths] for p in paths: relpath = os.path.relpath(p, r.path) if relpath.startswith('..' + os.path.sep): raise ValueError('path %r is not in repo' % relpath) # FIXME: Support patterns, directories. if ignore_manager.is_ignored(relpath): ignored.add(relpath) continue relpaths.append(relpath) r.stage(relpaths) return (relpaths, ignored) def _is_subdir(subdir, parentdir): """Check whether subdir is parentdir or a subdir of parentdir If parentdir or subdir is a relative path, it will be disamgibuated relative to the pwd. """ parentdir_abs = os.path.realpath(parentdir) + os.path.sep subdir_abs = os.path.realpath(subdir) + os.path.sep return subdir_abs.startswith(parentdir_abs) # TODO: option to remove ignored files also, in line with `git clean -fdx` def clean(repo=".", target_dir=None): """Remove any untracked files from the target directory recursively Equivalent to running `git clean -fd` in target_dir. Args: repo: Repository where the files may be tracked target_dir: Directory to clean - current directory if None """ if target_dir is None: target_dir = os.getcwd() with open_repo_closing(repo) as r: if not _is_subdir(target_dir, r.path): raise ValueError("target_dir must be in the repo's working dir") index = r.open_index() ignore_manager = IgnoreFilterManager.from_repo(r) paths_in_wd = _walk_working_dir_paths(target_dir, r.path) # Reverse file visit order, so that files and subdirectories are # removed before containing directory for ap, is_dir in reversed(list(paths_in_wd)): if is_dir: # All subdirectories and files have been removed if untracked, # so dir contains no tracked files iff it is empty. is_empty = len(os.listdir(ap)) == 0 if is_empty: os.rmdir(ap) else: ip = path_to_tree_path(r.path, ap) is_tracked = ip in index rp = os.path.relpath(ap, r.path) is_ignored = ignore_manager.is_ignored(rp) if not is_tracked and not is_ignored: os.remove(ap) def remove(repo=".", paths=None, cached=False): """Remove files from the staging area. Args: repo: Repository for the files paths: Paths to remove """ with open_repo_closing(repo) as r: index = r.open_index() for p in paths: - full_path = os.path.abspath(p).encode(sys.getfilesystemencoding()) + full_path = os.fsencode(os.path.abspath(p)) tree_path = path_to_tree_path(r.path, p) try: index_sha = index[tree_path].sha except KeyError: raise Exception('%s did not match any files' % p) if not cached: try: st = os.lstat(full_path) except OSError: pass else: try: blob = blob_from_path_and_stat(full_path, st) except IOError: pass else: try: committed_sha = tree_lookup_path( r.__getitem__, r[r.head()].tree, tree_path)[1] except KeyError: committed_sha = None if blob.id != index_sha and index_sha != committed_sha: raise Exception( 'file has staged content differing ' 'from both the file and head: %s' % p) if index_sha != committed_sha: raise Exception( 'file has staged changes: %s' % p) os.remove(full_path) del index[tree_path] index.write() rm = remove def commit_decode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding: encoding = commit.encoding.decode('ascii') else: encoding = default_encoding return contents.decode(encoding, "replace") def commit_encode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding: encoding = commit.encoding.decode('ascii') else: encoding = default_encoding return contents.encode(encoding) def print_commit(commit, decode, outstream=sys.stdout): """Write a human-readable commit log entry. Args: commit: A `Commit` object 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. Args: tag: A `Tag` object decode: Function for decoding bytes to unicode string outstream: A stream to write to """ outstream.write("Tagger: " + decode(tag.tagger) + "\n") time_tuple = time.gmtime(tag.tag_time + tag.tag_timezone) time_str = time.strftime("%a %b %d %Y %H:%M:%S", time_tuple) timezone_str = format_timezone(tag.tag_timezone).decode('ascii') outstream.write("Date: " + time_str + " " + timezone_str + "\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. Args: repo: A `Repo` object blob: A `Blob` object decode: Function for decoding bytes to unicode string 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. Args: repo: A `Repo` object commit: A `Commit` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ print_commit(commit, decode=decode, outstream=outstream) if commit.parents: parent_commit = repo[commit.parents[0]] base_tree = parent_commit.tree else: base_tree = None diffstream = BytesIO() write_tree_diff( diffstream, repo.object_store, base_tree, commit.tree) diffstream.seek(0) outstream.write(commit_decode(commit, diffstream.getvalue())) def show_tree(repo, tree, decode, outstream=sys.stdout): """Print a tree to a stream. Args: repo: A `Repo` object tree: A `Tree` object decode: Function for decoding bytes to unicode string 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. Args: repo: A `Repo` object tag: A `Tag` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ print_tag(tag, decode, outstream) show_object(repo, repo[tag.object[1]], decode, 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 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. Args: repo: Path to repository paths: Optional set of specific paths to print entries for outstream: Stream to write log output to reverse: Reverse order in which entries are printed name_status: Print name status 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: def decode(x): return 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. Args: repo: Path to repository objects: Objects to show (defaults to [HEAD]) outstream: Stream to write to 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): def decode(x): return commit_decode(o, x, default_encoding) else: def decode(x): return 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. Args: repo: Path to repository old_tree: Id of old tree new_tree: Id of new tree 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. Args: repo: Path to repository commits: Commits over which to iterate 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, sign=False): """Creates a tag in git via dulwich calls: Args: repo: Path to repository tag: tag string author: tag author (optional, if annotated is set) message: tag message (optional) annotated: whether to create an annotated tag objectish: object the tag should point at, defaults to HEAD tag_time: Optional time for annotated tag tag_timezone: Optional timezone for annotated tag sign: GPG Sign the 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(r.get_config_stack()) 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 if sign: import gpg with gpg.Context(armor=True) as c: tag_obj.signature, unused_result = c.sign( tag_obj.as_raw_string()) r.object_store.add_object(tag_obj) tag_id = tag_obj.id else: tag_id = object.id r.refs[_make_tag_ref(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. Args: repo: Path to repository outstream: Stream to write tags to """ with open_repo_closing(repo) as r: tags = sorted(r.refs.as_dict(b"refs/tags")) return tags def tag_delete(repo, name): """Remove a tag. Args: repo: Path to repository 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[_make_tag_ref(name)] def reset(repo, mode, treeish="HEAD"): """Reset current HEAD to the specified state. Args: repo: Path to repository mode: Mode ("hard", "soft", "mixed") treeish: Treeish to reset to """ if mode != "hard": raise ValueError("hard is the only mode currently supported") with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) r.reset_index(tree.id) def push(repo, remote_location, refspecs, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, **kwargs): """Remote push with dulwich via dulwich.client Args: repo: Path to repository remote_location: Location of the remote refspecs: Refs to push to remote outstream: A stream file to write output 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, config=r.get_config_stack(), **kwargs) 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, generate_pack_data=r.generate_pack_data, progress=errstream.write) errstream.write( b"Push to " + remote_location_bytes + b" successful.\n") except UpdateRefsError as e: errstream.write(b"Push to " + remote_location_bytes + b" failed -> " + e.message.encode(err_encoding) + b"\n") except SendPackError as e: errstream.write(b"Push to " + remote_location_bytes + b" failed -> " + e.args[0] + b"\n") def pull(repo, remote_location=None, refspecs=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, **kwargs): """Pull from remote via dulwich.client Args: repo: Path to repository remote_location: Location of the remote refspec: refspecs to fetch outstream: A stream file to write to output errstream: A stream file to write to errors """ # Open the repo with open_repo_closing(repo) as r: if remote_location is None: config = r.get_config() remote_name = get_branch_remote(r.path) section = (b'remote', remote_name) if config.has_section(section): url = config.get(section, 'url') remote_location = url.decode() 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, config=r.get_config_stack(), **kwargs) fetch_result = client.fetch( path, r, progress=errstream.write, determine_wants=determine_wants) for (lh, rh, force) in selected_refs: r.refs[rh] = fetch_result.refs[lh] if selected_refs: r[b'HEAD'] = fetch_result.refs[selected_refs[0][1]] # Perform 'git checkout .' - syncs staged changes tree = r[b"HEAD"].tree r.reset_index(tree=tree) def status(repo=".", ignored=False): """Returns staged, unstaged, and untracked changes relative to the HEAD. Args: repo: Path to repository or repository object ignored: Whether to include ignored files in `untracked` Returns: GitStatus tuple, staged - dict with lists 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 index = r.open_index() normalizer = r.get_blob_normalizer() filter_callback = normalizer.checkin_normalize unstaged_changes = list( get_unstaged_changes(index, r.path, filter_callback) ) ignore_manager = IgnoreFilterManager.from_repo(r) untracked_paths = get_untracked_paths(r.path, r.path, index) if ignored: untracked_changes = list(untracked_paths) else: untracked_changes = [ p for p in untracked_paths if not ignore_manager.is_ignored(p)] return GitStatus(tracked_changes, unstaged_changes, untracked_changes) def _walk_working_dir_paths(frompath, basepath): """Get path, is_dir for files in working dir from frompath Args: frompath: Path to begin walk basepath: Path to compare to """ for dirpath, dirnames, filenames in os.walk(frompath): # Skip .git and below. if '.git' in dirnames: dirnames.remove('.git') if dirpath != basepath: continue if '.git' in filenames: filenames.remove('.git') if dirpath != basepath: continue if dirpath != frompath: yield dirpath, True for filename in filenames: filepath = os.path.join(dirpath, filename) yield filepath, False def get_untracked_paths(frompath, basepath, index): """Get untracked paths. Args: ;param frompath: Path to walk basepath: Path to compare to index: Index to check against """ for ap, is_dir in _walk_working_dir_paths(frompath, basepath): if not is_dir: ip = path_to_tree_path(basepath, ap) if ip not in index: yield os.path.relpath(ap, frompath) def get_tree_changes(repo): """Return add/delete/modify changes to tree by comparing index to HEAD. Args: repo: repo path or object Returns: 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. Args: path: Path to the directory to serve. address: Optional address to listen on (defaults to ::) 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. Args: path: Path to the directory to serve address: Optional address to listen on (defaults to ::) 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. Args: path: Path to the repository inf: Input stream to communicate with client 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) path = os.path.expanduser(path) 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. Args: path: Path to the repository inf: Input stream to communicate with client 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) path = os.path.expanduser(path) 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 _make_branch_ref(name): if getattr(name, 'encode', None): name = name.encode(DEFAULT_ENCODING) return LOCAL_BRANCH_PREFIX + name def _make_tag_ref(name): if getattr(name, 'encode', None): name = name.encode(DEFAULT_ENCODING) return b"refs/tags/" + name def branch_delete(repo, name): """Delete a branch. Args: repo: Path to the repository name: Name of the branch """ with open_repo_closing(repo) as r: if isinstance(name, list): names = name else: names = [name] for name in names: del r.refs[_make_branch_ref(name)] def branch_create(repo, name, objectish=None, force=False): """Create a branch. Args: repo: Path to the repository name: Name of the new branch objectish: Target object to point new branch at (defaults to HEAD) force: Force creation of branch, even if it already exists """ with open_repo_closing(repo) as r: if objectish is None: objectish = "HEAD" object = parse_object(r, objectish) refname = _make_branch_ref(name) ref_message = b"branch: Created from " + objectish.encode('utf-8') if force: r.refs.set_if_equals(refname, None, object.id, message=ref_message) else: if not r.refs.add_if_new(refname, object.id, message=ref_message): raise KeyError("Branch with name %s already exists." % name) def branch_list(repo): """List all branches. Args: repo: Path to the repository """ with open_repo_closing(repo) as r: return r.refs.keys(base=LOCAL_BRANCH_PREFIX) def active_branch(repo): """Return the active branch in the repository, if any. Args: repo: Repository to open Returns: branch name Raises: KeyError: if the repository does not have a working tree IndexError: if HEAD is floating """ with open_repo_closing(repo) as r: active_ref = r.refs.follow(b'HEAD')[0][1] if not active_ref.startswith(LOCAL_BRANCH_PREFIX): raise ValueError(active_ref) return active_ref[len(LOCAL_BRANCH_PREFIX):] def get_branch_remote(repo): """Return the active branch's remote name, if any. Args: repo: Repository to open Returns: remote name Raises: KeyError: if the repository does not have a working tree """ with open_repo_closing(repo) as r: branch_name = active_branch(r.path) config = r.get_config() try: remote_name = config.get((b'branch', branch_name), 'remote') except KeyError: remote_name = b'origin' return remote_name def fetch(repo, remote_location, remote_name=b'origin', outstream=sys.stdout, errstream=default_bytes_err_stream, message=None, depth=None, prune=False, prune_tags=False, **kwargs): """Fetch objects from a remote server. Args: repo: Path to the repository remote_location: String identifying a remote server remote_name: Name for remote server outstream: Output stream (defaults to stdout) errstream: Error stream (defaults to stderr) message: Reflog message (defaults to b"fetch: from ") depth: Depth to fetch at prune: Prune remote removed refs prune_tags: Prune reomte removed tags Returns: Dictionary with refs on the remote """ if message is None: message = b'fetch: from ' + remote_location.encode("utf-8") with open_repo_closing(repo) as r: client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs) fetch_result = client.fetch(path, r, progress=errstream.write, depth=depth) stripped_refs = strip_peeled_refs(fetch_result.refs) branches = { n[len(LOCAL_BRANCH_PREFIX):]: v for (n, v) in stripped_refs.items() if n.startswith(LOCAL_BRANCH_PREFIX)} r.refs.import_refs( b'refs/remotes/' + remote_name, branches, message=message, prune=prune) tags = { n[len(b'refs/tags/'):]: v for (n, v) in stripped_refs.items() if n.startswith(b'refs/tags/') and not n.endswith(ANNOTATED_TAG_SUFFIX)} r.refs.import_refs( b'refs/tags', tags, message=message, prune=prune_tags) return fetch_result.refs def ls_remote(remote, config=None, **kwargs): """List the refs in a remote. Args: remote: Remote repository location config: Configuration to use Returns: Dictionary with remote refs """ if config is None: config = StackedConfig.default() client, host_path = get_transport_and_path(remote, config=config, **kwargs) return client.get_refs(host_path) def repack(repo): """Repack loose files in a repository. Currently this only packs loose objects. Args: 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. Args: repo: Path to the repository object_ids: List of object ids to write packf: File-like object to write to 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 = sorted([(k, v[0], v[1]) for (k, v) in entries.items()]) write_pack_index(idxf, entries, data_sum) def ls_tree(repo, treeish=b"HEAD", outstream=sys.stdout, recursive=False, name_only=False): """List contents of a tree. Args: repo: Path to the repository tree_ish: Tree id to list outstream: Output stream (defaults to stdout) recursive: Whether to recursively list files 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) and recursive: list_tree(store, sha, name) with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) list_tree(r.object_store, tree.id, "") def remote_add(repo, name, url): """Add a remote. Args: repo: Path to the repository name: Remote name url: Remote URL """ if not isinstance(name, bytes): name = name.encode(DEFAULT_ENCODING) if not isinstance(url, bytes): url = url.encode(DEFAULT_ENCODING) with open_repo_closing(repo) as r: c = r.get_config() section = (b'remote', name) if c.has_section(section): raise RemoteExists(section) c.set(section, b"url", url) c.write_to_path() def check_ignore(repo, paths, no_index=False): """Debug gitignore files. Args: repo: Path to the repository paths: List of paths to check for no_index: Don't check index Returns: List of ignored files """ with open_repo_closing(repo) as r: index = r.open_index() ignore_manager = IgnoreFilterManager.from_repo(r) for path in paths: if not no_index and path_to_tree_path(r.path, path) in index: continue if os.path.isabs(path): path = os.path.relpath(path, r.path) if ignore_manager.is_ignored(path): yield path def update_head(repo, target, detached=False, new_branch=None): """Update HEAD to point at a new branch/commit. Note that this does not actually update the working tree. Args: repo: Path to the repository detach: Create a detached head target: Branch or committish to switch to new_branch: New branch to create """ with open_repo_closing(repo) as r: if new_branch is not None: to_set = _make_branch_ref(new_branch) else: to_set = b"HEAD" if detached: # TODO(jelmer): Provide some way so that the actual ref gets # updated rather than what it points to, so the delete isn't # necessary. del r.refs[to_set] r.refs[to_set] = parse_commit(r, target).id else: r.refs.set_symbolic_ref(to_set, parse_ref(r, target)) if new_branch is not None: r.refs.set_symbolic_ref(b"HEAD", to_set) def check_mailmap(repo, contact): """Check canonical name and email of contact. Args: repo: Path to the repository contact: Contact name and/or email Returns: Canonical contact data """ with open_repo_closing(repo) as r: from dulwich.mailmap import Mailmap import errno try: mailmap = Mailmap.from_path(os.path.join(r.path, '.mailmap')) except IOError as e: if e.errno != errno.ENOENT: raise mailmap = Mailmap() return mailmap.lookup(contact) def fsck(repo): """Check a repository. Args: repo: A path to the repository Returns: Iterator over errors/warnings """ with open_repo_closing(repo) as r: # TODO(jelmer): check pack files # TODO(jelmer): check graph # TODO(jelmer): check refs for sha in r.object_store: o = r.object_store[sha] try: o.check() except Exception as e: yield (sha, e) def stash_list(repo): """List all stashes in a repository.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) return enumerate(list(stash.stashes())) def stash_push(repo): """Push a new stash onto the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.push() def stash_pop(repo): """Pop a new stash from the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.pop() def ls_files(repo): """List all files in an index.""" with open_repo_closing(repo) as r: return sorted(r.open_index()) def describe(repo): """Describe the repository version. Args: projdir: git repository root Returns: a string description of the current git revision Examples: "gabcdefh", "v0.1" or "v0.1-5-gabcdefh". """ # Get the repository with open_repo_closing(repo) as r: # Get a list of all tags refs = r.get_refs() tags = {} for key, value in refs.items(): key = key.decode() obj = r.get_object(value) if u'tags' not in key: continue _, tag = key.rsplit(u'/', 1) try: commit = obj.object except AttributeError: continue else: commit = r.get_object(commit[1]) tags[tag] = [ datetime.datetime(*time.gmtime(commit.commit_time)[:6]), commit.id.decode('ascii'), ] sorted_tags = sorted(tags.items(), key=lambda tag: tag[1][0], reverse=True) # If there are no tags, return the current commit if len(sorted_tags) == 0: return 'g{}'.format(r[r.head()].id.decode('ascii')[:7]) # We're now 0 commits from the top commit_count = 0 # Get the latest commit latest_commit = r[r.head()] # Walk through all commits walker = r.get_walker() for entry in walker: # Check if tag commit_id = entry.commit.id.decode('ascii') for tag in sorted_tags: tag_name = tag[0] tag_commit = tag[1][1] if commit_id == tag_commit: if commit_count == 0: return tag_name else: return '{}-{}-g{}'.format( tag_name, commit_count, latest_commit.id.decode('ascii')[:7]) commit_count += 1 # Return plain commit if no parent tag can be found return 'g{}'.format(latest_commit.id.decode('ascii')[:7]) def get_object_by_path(repo, path, committish=None): """Get an object by path. Args: repo: A path to the repository path: Path to look up committish: Commit to look up path in Returns: A `ShaFile` object """ if committish is None: committish = "HEAD" # Get the repository with open_repo_closing(repo) as r: commit = parse_commit(r, committish) base_tree = commit.tree if not isinstance(path, bytes): path = commit_encode(commit, path) (mode, sha) = tree_lookup_path( r.object_store.__getitem__, base_tree, path) return r[sha] def write_tree(repo): """Write a tree object from the index. Args: repo: Repository for which to write tree Returns: tree id for the tree that was written """ with open_repo_closing(repo) as r: return r.open_index().commit(r.object_store) diff --git a/dulwich/refs.py b/dulwich/refs.py index d597289d..1e27feac 100644 --- a/dulwich/refs.py +++ b/dulwich/refs.py @@ -1,972 +1,972 @@ # refs.py -- For dealing with git refs # 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. # """Ref handling. """ import errno import os import sys from dulwich.errors import ( PackedRefsException, RefFormatError, ) from dulwich.objects import ( git_line, valid_hexsha, ZERO_SHA, ) from dulwich.file import ( GitFile, ensure_dir_exists, ) SYMREF = b'ref: ' LOCAL_BRANCH_PREFIX = b'refs/heads/' LOCAL_TAG_PREFIX = b'refs/tags/' BAD_REF_CHARS = set(b'\177 ~^:?*[') ANNOTATED_TAG_SUFFIX = b'^{}' def parse_symref_value(contents): """Parse a symref value. Args: contents: Contents to parse Returns: Destination """ if contents.startswith(SYMREF): return contents[len(SYMREF):].rstrip(b'\r\n') raise ValueError(contents) def check_ref_format(refname): """Check if a refname is correctly formatted. Implements all the same rules as git-check-ref-format[1]. [1] http://www.kernel.org/pub/software/scm/git/docs/git-check-ref-format.html Args: refname: The refname to check Returns: True if refname is valid, False otherwise """ # These could be combined into one big expression, but are listed # separately to parallel [1]. if b'/.' in refname or refname.startswith(b'.'): return False if b'/' not in refname: return False if b'..' in refname: return False for i, c in enumerate(refname): if ord(refname[i:i+1]) < 0o40 or c in BAD_REF_CHARS: return False if refname[-1] in b'/.': return False if refname.endswith(b'.lock'): return False if b'@{' in refname: return False if b'\\' in refname: return False return True class RefsContainer(object): """A container for refs.""" def __init__(self, logger=None): self._logger = logger def _log(self, ref, old_sha, new_sha, committer=None, timestamp=None, timezone=None, message=None): if self._logger is None: return if message is None: return self._logger(ref, old_sha, new_sha, committer, timestamp, timezone, message) def set_symbolic_ref(self, name, other, committer=None, timestamp=None, timezone=None, message=None): """Make a ref point at another ref. Args: name: Name of the ref to set other: Name of the ref to point at message: Optional message """ raise NotImplementedError(self.set_symbolic_ref) def get_packed_refs(self): """Get contents of the packed-refs file. Returns: Dictionary mapping ref names to SHA1s Note: Will return an empty dictionary when no packed-refs file is present. """ raise NotImplementedError(self.get_packed_refs) def get_peeled(self, name): """Return the cached peeled value of a ref, if available. Args: name: Name of the ref to peel Returns: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If the ref may point to a tag, but no cached information is available, None is returned. """ return None def import_refs(self, base, other, committer=None, timestamp=None, timezone=None, message=None, prune=False): if prune: to_delete = set(self.subkeys(base)) else: to_delete = set() for name, value in other.items(): self.set_if_equals(b'/'.join((base, name)), None, value, message=message) if to_delete: try: to_delete.remove(name) except KeyError: pass for ref in to_delete: self.remove_if_equals(b'/'.join((base, ref)), None) def allkeys(self): """All refs present in this container.""" raise NotImplementedError(self.allkeys) def __iter__(self): return iter(self.allkeys()) def keys(self, base=None): """Refs present in this container. Args: base: An optional base to return refs under. Returns: An unsorted set of valid refs in this container, including packed refs. """ if base is not None: return self.subkeys(base) else: return self.allkeys() def subkeys(self, base): """Refs present in this container under a base. Args: base: The base to return refs under. Returns: A set of valid refs in this container under the base; the base prefix is stripped from the ref names returned. """ keys = set() base_len = len(base) + 1 for refname in self.allkeys(): if refname.startswith(base): keys.add(refname[base_len:]) return keys def as_dict(self, base=None): """Return the contents of this container as a dictionary. """ ret = {} keys = self.keys(base) if base is None: base = b'' else: base = base.rstrip(b'/') for key in keys: try: ret[key] = self[(base + b'/' + key).strip(b'/')] except KeyError: continue # Unable to resolve return ret def _check_refname(self, name): """Ensure a refname is valid and lives in refs or is HEAD. HEAD is not a valid refname according to git-check-ref-format, but this class needs to be able to touch HEAD. Also, check_ref_format expects refnames without the leading 'refs/', but this class requires that so it cannot touch anything outside the refs dir (or HEAD). Args: name: The name of the reference. Raises: KeyError: if a refname is not HEAD or is otherwise not valid. """ if name in (b'HEAD', b'refs/stash'): return if not name.startswith(b'refs/') or not check_ref_format(name[5:]): raise RefFormatError(name) def read_ref(self, refname): """Read a reference without following any references. Args: refname: The name of the reference Returns: The contents of the ref file, or None if it does not exist. """ contents = self.read_loose_ref(refname) if not contents: contents = self.get_packed_refs().get(refname, None) return contents def read_loose_ref(self, name): """Read a loose reference and return its contents. Args: name: the refname to read Returns: The contents of the ref file, or None if it does not exist. """ raise NotImplementedError(self.read_loose_ref) def follow(self, name): """Follow a reference name. Returns: a tuple of (refnames, sha), wheres refnames are the names of references in the chain """ contents = SYMREF + name depth = 0 refnames = [] while contents.startswith(SYMREF): refname = contents[len(SYMREF):] refnames.append(refname) contents = self.read_ref(refname) if not contents: break depth += 1 if depth > 5: raise KeyError(name) return refnames, contents def _follow(self, name): import warnings warnings.warn( "RefsContainer._follow is deprecated. Use RefsContainer.follow " "instead.", DeprecationWarning) refnames, contents = self.follow(name) if not refnames: return (None, contents) return (refnames[-1], contents) def __contains__(self, refname): if self.read_ref(refname): return True return False def __getitem__(self, name): """Get the SHA1 for a reference name. This method follows all symbolic references. """ _, sha = self.follow(name) if sha is None: raise KeyError(name) return sha def set_if_equals(self, name, old_ref, new_ref, committer=None, timestamp=None, timezone=None, message=None): """Set a refname to new_ref only if it currently equals old_ref. This method follows all symbolic references if applicable for the subclass, and can be used to perform an atomic compare-and-swap operation. Args: name: The refname to set. old_ref: The old sha the refname must refer to, or None to set unconditionally. new_ref: The new sha the refname will refer to. message: Message for reflog Returns: True if the set was successful, False otherwise. """ raise NotImplementedError(self.set_if_equals) def add_if_new(self, name, ref): """Add a new reference only if it does not already exist. Args: name: Ref name ref: Ref value message: Message for reflog """ raise NotImplementedError(self.add_if_new) def __setitem__(self, name, ref): """Set a reference name to point to the given SHA1. This method follows all symbolic references if applicable for the subclass. Note: This method unconditionally overwrites the contents of a reference. To update atomically only if the reference has not changed, use set_if_equals(). Args: name: The refname to set. ref: The new sha the refname will refer to. """ self.set_if_equals(name, None, ref) def remove_if_equals(self, name, old_ref, committer=None, timestamp=None, timezone=None, message=None): """Remove a refname only if it currently equals old_ref. This method does not follow symbolic references, even if applicable for the subclass. It can be used to perform an atomic compare-and-delete operation. Args: name: The refname to delete. old_ref: The old sha the refname must refer to, or None to delete unconditionally. message: Message for reflog Returns: True if the delete was successful, False otherwise. """ raise NotImplementedError(self.remove_if_equals) def __delitem__(self, name): """Remove a refname. This method does not follow symbolic references, even if applicable for the subclass. Note: This method unconditionally deletes the contents of a reference. To delete atomically only if the reference has not changed, use remove_if_equals(). Args: name: The refname to delete. """ self.remove_if_equals(name, None) def get_symrefs(self): """Get a dict with all symrefs in this container. Returns: Dictionary mapping source ref to target ref """ ret = {} for src in self.allkeys(): try: dst = parse_symref_value(self.read_ref(src)) except ValueError: pass else: ret[src] = dst return ret class DictRefsContainer(RefsContainer): """RefsContainer backed by a simple dict. This container does not support symbolic or packed references and is not threadsafe. """ def __init__(self, refs, logger=None): super(DictRefsContainer, self).__init__(logger=logger) self._refs = refs self._peeled = {} def allkeys(self): return self._refs.keys() def read_loose_ref(self, name): return self._refs.get(name, None) def get_packed_refs(self): return {} def set_symbolic_ref(self, name, other, committer=None, timestamp=None, timezone=None, message=None): old = self.follow(name)[-1] self._refs[name] = SYMREF + other self._log(name, old, old, committer=committer, timestamp=timestamp, timezone=timezone, message=message) def set_if_equals(self, name, old_ref, new_ref, committer=None, timestamp=None, timezone=None, message=None): if old_ref is not None and self._refs.get(name, ZERO_SHA) != old_ref: return False realnames, _ = self.follow(name) for realname in realnames: self._check_refname(realname) old = self._refs.get(realname) self._refs[realname] = new_ref self._log(realname, old, new_ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def add_if_new(self, name, ref, committer=None, timestamp=None, timezone=None, message=None): if name in self._refs: return False self._refs[name] = ref self._log(name, None, ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def remove_if_equals(self, name, old_ref, committer=None, timestamp=None, timezone=None, message=None): if old_ref is not None and self._refs.get(name, ZERO_SHA) != old_ref: return False try: old = self._refs.pop(name) except KeyError: pass else: self._log(name, old, None, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def get_peeled(self, name): return self._peeled.get(name) def _update(self, refs): """Update multiple refs; intended only for testing.""" # TODO(dborowitz): replace this with a public function that uses # set_if_equal. self._refs.update(refs) def _update_peeled(self, peeled): """Update cached peeled refs; intended only for testing.""" self._peeled.update(peeled) class InfoRefsContainer(RefsContainer): """Refs container that reads refs from a info/refs file.""" def __init__(self, f): self._refs = {} self._peeled = {} for l in f.readlines(): sha, name = l.rstrip(b'\n').split(b'\t') if name.endswith(ANNOTATED_TAG_SUFFIX): name = name[:-3] if not check_ref_format(name): raise ValueError("invalid ref name %r" % name) self._peeled[name] = sha else: if not check_ref_format(name): raise ValueError("invalid ref name %r" % name) self._refs[name] = sha def allkeys(self): return self._refs.keys() def read_loose_ref(self, name): return self._refs.get(name, None) def get_packed_refs(self): return {} def get_peeled(self, name): try: return self._peeled[name] except KeyError: return self._refs[name] class DiskRefsContainer(RefsContainer): """Refs container that reads refs from disk.""" def __init__(self, path, worktree_path=None, logger=None): super(DiskRefsContainer, self).__init__(logger=logger) if getattr(path, 'encode', None) is not None: - path = path.encode(sys.getfilesystemencoding()) + path = os.fsencode(path) self.path = path if worktree_path is None: worktree_path = path if getattr(worktree_path, 'encode', None) is not None: - worktree_path = worktree_path.encode(sys.getfilesystemencoding()) + worktree_path = os.fsencode(worktree_path) self.worktree_path = worktree_path self._packed_refs = None self._peeled_refs = None def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self.path) def subkeys(self, base): subkeys = set() path = self.refpath(base) for root, unused_dirs, files in os.walk(path): dir = root[len(path):] if os.path.sep != '/': dir = dir.replace(os.path.sep.encode( sys.getfilesystemencoding()), b"/") dir = dir.strip(b'/') for filename in files: refname = b"/".join(([dir] if dir else []) + [filename]) # check_ref_format requires at least one /, so we prepend the # base before calling it. if check_ref_format(base + b'/' + refname): subkeys.add(refname) for key in self.get_packed_refs(): if key.startswith(base): subkeys.add(key[len(base):].strip(b'/')) return subkeys def allkeys(self): allkeys = set() if os.path.exists(self.refpath(b'HEAD')): allkeys.add(b'HEAD') path = self.refpath(b'') refspath = self.refpath(b'refs') for root, unused_dirs, files in os.walk(refspath): dir = root[len(path):] if os.path.sep != '/': dir = dir.replace( os.path.sep.encode(sys.getfilesystemencoding()), b"/") for filename in files: refname = b"/".join([dir, filename]) if check_ref_format(refname): allkeys.add(refname) allkeys.update(self.get_packed_refs()) return allkeys def refpath(self, name): """Return the disk path of a ref. """ if os.path.sep != "/": name = name.replace( b"/", os.path.sep.encode(sys.getfilesystemencoding())) # TODO: as the 'HEAD' reference is working tree specific, it # should actually not be a part of RefsContainer if name == b'HEAD': return os.path.join(self.worktree_path, name) else: return os.path.join(self.path, name) def get_packed_refs(self): """Get contents of the packed-refs file. Returns: Dictionary mapping ref names to SHA1s Note: Will return an empty dictionary when no packed-refs file is present. """ # TODO: invalidate the cache on repacking if self._packed_refs is None: # set both to empty because we want _peeled_refs to be # None if and only if _packed_refs is also None. self._packed_refs = {} self._peeled_refs = {} path = os.path.join(self.path, b'packed-refs') try: f = GitFile(path, 'rb') except IOError as e: if e.errno == errno.ENOENT: return {} raise with f: first_line = next(iter(f)).rstrip() if (first_line.startswith(b'# pack-refs') and b' peeled' in first_line): for sha, name, peeled in read_packed_refs_with_peeled(f): self._packed_refs[name] = sha if peeled: self._peeled_refs[name] = peeled else: f.seek(0) for sha, name in read_packed_refs(f): self._packed_refs[name] = sha return self._packed_refs def get_peeled(self, name): """Return the cached peeled value of a ref, if available. Args: name: Name of the ref to peel Returns: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If the ref may point to a tag, but no cached information is available, None is returned. """ self.get_packed_refs() if self._peeled_refs is None or name not in self._packed_refs: # No cache: no peeled refs were read, or this ref is loose return None if name in self._peeled_refs: return self._peeled_refs[name] else: # Known not peelable return self[name] def read_loose_ref(self, name): """Read a reference file and return its contents. If the reference file a symbolic reference, only read the first line of the file. Otherwise, only read the first 40 bytes. Args: name: the refname to read, relative to refpath Returns: The contents of the ref file, or None if the file does not exist. Raises: IOError: if any other error occurs """ filename = self.refpath(name) try: with GitFile(filename, 'rb') as f: header = f.read(len(SYMREF)) if header == SYMREF: # Read only the first line return header + next(iter(f)).rstrip(b'\r\n') else: # Read only the first 40 bytes return header + f.read(40 - len(SYMREF)) except IOError as e: if e.errno in (errno.ENOENT, errno.EISDIR, errno.ENOTDIR): return None raise def _remove_packed_ref(self, name): if self._packed_refs is None: return filename = os.path.join(self.path, b'packed-refs') # reread cached refs from disk, while holding the lock f = GitFile(filename, 'wb') try: self._packed_refs = None self.get_packed_refs() if name not in self._packed_refs: return del self._packed_refs[name] if name in self._peeled_refs: del self._peeled_refs[name] write_packed_refs(f, self._packed_refs, self._peeled_refs) f.close() finally: f.abort() def set_symbolic_ref(self, name, other, committer=None, timestamp=None, timezone=None, message=None): """Make a ref point at another ref. Args: name: Name of the ref to set other: Name of the ref to point at message: Optional message to describe the change """ self._check_refname(name) self._check_refname(other) filename = self.refpath(name) f = GitFile(filename, 'wb') try: f.write(SYMREF + other + b'\n') sha = self.follow(name)[-1] self._log(name, sha, sha, committer=committer, timestamp=timestamp, timezone=timezone, message=message) except BaseException: f.abort() raise else: f.close() def set_if_equals(self, name, old_ref, new_ref, committer=None, timestamp=None, timezone=None, message=None): """Set a refname to new_ref only if it currently equals old_ref. This method follows all symbolic references, and can be used to perform an atomic compare-and-swap operation. Args: name: The refname to set. old_ref: The old sha the refname must refer to, or None to set unconditionally. new_ref: The new sha the refname will refer to. message: Set message for reflog Returns: True if the set was successful, False otherwise. """ self._check_refname(name) try: realnames, _ = self.follow(name) realname = realnames[-1] except (KeyError, IndexError): realname = name filename = self.refpath(realname) # make sure none of the ancestor folders is in packed refs probe_ref = os.path.dirname(realname) packed_refs = self.get_packed_refs() while probe_ref: if packed_refs.get(probe_ref, None) is not None: raise OSError(errno.ENOTDIR, 'Not a directory: {}'.format(filename)) probe_ref = os.path.dirname(probe_ref) ensure_dir_exists(os.path.dirname(filename)) with GitFile(filename, 'wb') as f: if old_ref is not None: try: # read again while holding the lock orig_ref = self.read_loose_ref(realname) if orig_ref is None: orig_ref = self.get_packed_refs().get( realname, ZERO_SHA) if orig_ref != old_ref: f.abort() return False except (OSError, IOError): f.abort() raise try: f.write(new_ref + b'\n') except (OSError, IOError): f.abort() raise self._log(realname, old_ref, new_ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def add_if_new(self, name, ref, committer=None, timestamp=None, timezone=None, message=None): """Add a new reference only if it does not already exist. This method follows symrefs, and only ensures that the last ref in the chain does not exist. Args: name: The refname to set. ref: The new sha the refname will refer to. message: Optional message for reflog Returns: True if the add was successful, False otherwise. """ try: realnames, contents = self.follow(name) if contents is not None: return False realname = realnames[-1] except (KeyError, IndexError): realname = name self._check_refname(realname) filename = self.refpath(realname) ensure_dir_exists(os.path.dirname(filename)) with GitFile(filename, 'wb') as f: if os.path.exists(filename) or name in self.get_packed_refs(): f.abort() return False try: f.write(ref + b'\n') except (OSError, IOError): f.abort() raise else: self._log(name, None, ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def remove_if_equals(self, name, old_ref, committer=None, timestamp=None, timezone=None, message=None): """Remove a refname only if it currently equals old_ref. This method does not follow symbolic references. It can be used to perform an atomic compare-and-delete operation. Args: name: The refname to delete. old_ref: The old sha the refname must refer to, or None to delete unconditionally. message: Optional message Returns: True if the delete was successful, False otherwise. """ self._check_refname(name) filename = self.refpath(name) ensure_dir_exists(os.path.dirname(filename)) f = GitFile(filename, 'wb') try: if old_ref is not None: orig_ref = self.read_loose_ref(name) if orig_ref is None: orig_ref = self.get_packed_refs().get(name, ZERO_SHA) if orig_ref != old_ref: return False # remove the reference file itself try: os.remove(filename) except OSError as e: if e.errno != errno.ENOENT: # may only be packed raise self._remove_packed_ref(name) self._log(name, old_ref, None, committer=committer, timestamp=timestamp, timezone=timezone, message=message) finally: # never write, we just wanted the lock f.abort() # outside of the lock, clean-up any parent directory that might now # be empty. this ensures that re-creating a reference of the same # name of what was previously a directory works as expected parent = name while True: try: parent, _ = parent.rsplit(b'/', 1) except ValueError: break parent_filename = self.refpath(parent) try: os.rmdir(parent_filename) except OSError: # this can be caused by the parent directory being # removed by another process, being not empty, etc. # in any case, this is non fatal because we already # removed the reference, just ignore it break return True def _split_ref_line(line): """Split a single ref line into a tuple of SHA1 and name.""" fields = line.rstrip(b'\n\r').split(b' ') if len(fields) != 2: raise PackedRefsException("invalid ref line %r" % line) sha, name = fields if not valid_hexsha(sha): raise PackedRefsException("Invalid hex sha %r" % sha) if not check_ref_format(name): raise PackedRefsException("invalid ref name %r" % name) return (sha, name) def read_packed_refs(f): """Read a packed refs file. Args: f: file-like object to read from Returns: Iterator over tuples with SHA1s and ref names. """ for l in f: if l.startswith(b'#'): # Comment continue if l.startswith(b'^'): raise PackedRefsException( "found peeled ref in packed-refs without peeled") yield _split_ref_line(l) def read_packed_refs_with_peeled(f): """Read a packed refs file including peeled refs. Assumes the "# pack-refs with: peeled" line was already read. Yields tuples with ref names, SHA1s, and peeled SHA1s (or None). Args: f: file-like object to read from, seek'ed to the second line """ last = None for line in f: if line[0] == b'#': continue line = line.rstrip(b'\r\n') if line.startswith(b'^'): if not last: raise PackedRefsException("unexpected peeled ref line") if not valid_hexsha(line[1:]): raise PackedRefsException("Invalid hex sha %r" % line[1:]) sha, name = _split_ref_line(last) last = None yield (sha, name, line[1:]) else: if last: sha, name = _split_ref_line(last) yield (sha, name, None) last = line if last: sha, name = _split_ref_line(last) yield (sha, name, None) def write_packed_refs(f, packed_refs, peeled_refs=None): """Write a packed refs file. Args: f: empty file-like object to write to packed_refs: dict of refname to sha of packed refs to write peeled_refs: dict of refname to peeled value of sha """ if peeled_refs is None: peeled_refs = {} else: f.write(b'# pack-refs with: peeled\n') for refname in sorted(packed_refs.keys()): f.write(git_line(packed_refs[refname], refname)) if refname in peeled_refs: f.write(b'^' + peeled_refs[refname] + b'\n') def read_info_refs(f): ret = {} for l in f.readlines(): (sha, name) = l.rstrip(b"\r\n").split(b"\t", 1) ret[name] = sha return ret def write_info_refs(refs, store): """Generate info refs.""" for name, sha in sorted(refs.items()): # get_refs() includes HEAD as a special case, but we don't want to # advertise it if name == b'HEAD': continue try: o = store[sha] except KeyError: continue peeled = store.peel_sha(sha) yield o.id + b'\t' + name + b'\n' if o.id != peeled.id: yield peeled.id + b'\t' + name + ANNOTATED_TAG_SUFFIX + b'\n' def is_local_branch(x): return x.startswith(LOCAL_BRANCH_PREFIX) def strip_peeled_refs(refs): """Remove all peeled refs""" return {ref: sha for (ref, sha) in refs.items() if not ref.endswith(ANNOTATED_TAG_SUFFIX)} diff --git a/dulwich/repo.py b/dulwich/repo.py index f8e8245e..307b4f61 100644 --- a/dulwich/repo.py +++ b/dulwich/repo.py @@ -1,1498 +1,1493 @@ # repo.py -- For dealing with git repositories. # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Repository access. This module contains the base class for git repositories (BaseRepo) and an implementation which uses a repository on local disk (Repo). """ from io import BytesIO import errno import os import sys import stat import time from dulwich.errors import ( NoIndexPresent, NotBlobError, NotCommitError, NotGitRepository, NotTreeError, NotTagError, CommitError, RefFormatError, HookError, ) from dulwich.file import ( GitFile, ) from dulwich.object_store import ( DiskObjectStore, MemoryObjectStore, ObjectStoreGraphWalker, ) from dulwich.objects import ( check_hexsha, Blob, Commit, ShaFile, Tag, Tree, ) from dulwich.pack import ( pack_objects_to_data, ) from dulwich.hooks import ( PreCommitShellHook, PostCommitShellHook, CommitMsgShellHook, PostReceiveShellHook, ) from dulwich.line_ending import BlobNormalizer from dulwich.refs import ( # noqa: F401 ANNOTATED_TAG_SUFFIX, check_ref_format, RefsContainer, DictRefsContainer, InfoRefsContainer, DiskRefsContainer, read_packed_refs, read_packed_refs_with_peeled, write_packed_refs, SYMREF, ) import warnings CONTROLDIR = '.git' OBJECTDIR = 'objects' REFSDIR = 'refs' REFSDIR_TAGS = 'tags' REFSDIR_HEADS = 'heads' INDEX_FILENAME = "index" COMMONDIR = 'commondir' GITDIR = 'gitdir' WORKTREES = 'worktrees' BASE_DIRECTORIES = [ ["branches"], [REFSDIR], [REFSDIR, REFSDIR_TAGS], [REFSDIR, REFSDIR_HEADS], ["hooks"], ["info"] ] DEFAULT_REF = b'refs/heads/master' class InvalidUserIdentity(Exception): """User identity is not of the format 'user '""" def __init__(self, identity): self.identity = identity def _get_default_identity(): import getpass import socket username = getpass.getuser() try: import pwd except ImportError: fullname = None else: try: gecos = pwd.getpwnam(username).pw_gecos except KeyError: fullname = None else: fullname = gecos.split(',')[0] if not fullname: fullname = username email = os.environ.get('EMAIL') if email is None: email = "{}@{}".format(username, socket.gethostname()) return (fullname, email) def get_user_identity(config, kind=None): """Determine the identity to use for new commits. """ if kind: user = os.environ.get("GIT_" + kind + "_NAME") if user is not None: user = user.encode('utf-8') email = os.environ.get("GIT_" + kind + "_EMAIL") if email is not None: email = email.encode('utf-8') else: user = None email = None if user is None: try: user = config.get(("user", ), "name") except KeyError: user = None if email is None: try: email = config.get(("user", ), "email") except KeyError: email = None default_user, default_email = _get_default_identity() if user is None: user = default_user if not isinstance(user, bytes): user = user.encode('utf-8') if email is None: email = default_email if not isinstance(email, bytes): email = email.encode('utf-8') if email.startswith(b'<') and email.endswith(b'>'): email = email[1:-1] return (user + b" <" + email + b">") def check_user_identity(identity): """Verify that a user identity is formatted correctly. Args: identity: User identity bytestring Raises: InvalidUserIdentity: Raised when identity is invalid """ try: fst, snd = identity.split(b' <', 1) except ValueError: raise InvalidUserIdentity(identity) if b'>' not in snd: raise InvalidUserIdentity(identity) def parse_graftpoints(graftpoints): """Convert a list of graftpoints into a dict Args: graftpoints: Iterator of graftpoint lines Each line is formatted as: []* Resulting dictionary is: : [*] https://git.wiki.kernel.org/index.php/GraftPoint """ grafts = {} for l in graftpoints: raw_graft = l.split(None, 1) commit = raw_graft[0] if len(raw_graft) == 2: parents = raw_graft[1].split() else: parents = [] for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') grafts[commit] = parents return grafts def serialize_graftpoints(graftpoints): """Convert a dictionary of grafts into string The graft dictionary is: : [*] Each line is formatted as: []* https://git.wiki.kernel.org/index.php/GraftPoint """ graft_lines = [] for commit, parents in graftpoints.items(): if parents: graft_lines.append(commit + b' ' + b' '.join(parents)) else: graft_lines.append(commit) return b'\n'.join(graft_lines) def _set_filesystem_hidden(path): """Mark path as to be hidden if supported by platform and filesystem. On win32 uses SetFileAttributesW api: """ if sys.platform == 'win32': import ctypes from ctypes.wintypes import BOOL, DWORD, LPCWSTR FILE_ATTRIBUTE_HIDDEN = 2 SetFileAttributesW = ctypes.WINFUNCTYPE(BOOL, LPCWSTR, DWORD)( ("SetFileAttributesW", ctypes.windll.kernel32)) if isinstance(path, bytes): - path = path.decode(sys.getfilesystemencoding()) + path = os.fsdecode(path) if not SetFileAttributesW(path, FILE_ATTRIBUTE_HIDDEN): pass # Could raise or log `ctypes.WinError()` here # Could implement other platform specific filesytem hiding here class BaseRepo(object): """Base class for a git repository. :ivar object_store: Dictionary-like object for accessing the objects :ivar refs: Dictionary-like object with the refs in this repository """ def __init__(self, object_store, refs): """Open a repository. This shouldn't be called directly, but rather through one of the base classes, such as MemoryRepo or Repo. Args: object_store: Object store to use refs: Refs container to use """ self.object_store = object_store self.refs = refs self._graftpoints = {} self.hooks = {} def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ raise NotImplementedError(self._determine_file_mode) def _init_files(self, bare): """Initialize a default set of named files.""" from dulwich.config import ConfigFile self._put_named_file('description', b"Unnamed repository") f = BytesIO() cf = ConfigFile() cf.set("core", "repositoryformatversion", "0") if self._determine_file_mode(): cf.set("core", "filemode", True) else: cf.set("core", "filemode", False) cf.set("core", "bare", bare) cf.set("core", "logallrefupdates", True) cf.write_to_file(f) self._put_named_file('config', f.getvalue()) self._put_named_file(os.path.join('info', 'exclude'), b'') def get_named_file(self, path): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. Returns: An open file object, or None if the file does not exist. """ raise NotImplementedError(self.get_named_file) def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ raise NotImplementedError(self._put_named_file) def _del_named_file(self, path): """Delete a file in the contrl directory with the given name.""" raise NotImplementedError(self._del_named_file) def open_index(self): """Open the index for this repository. Raises: NoIndexPresent: If no index is present Returns: The matching `Index` """ raise NotImplementedError(self.open_index) def fetch(self, target, determine_wants=None, progress=None, depth=None): """Fetch objects into another repository. Args: target: The target repository determine_wants: Optional function to determine what refs to fetch. progress: Optional progress function depth: Optional shallow fetch depth Returns: The local refs """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all count, pack_data = self.fetch_pack_data( determine_wants, target.get_graph_walker(), progress=progress, depth=depth) target.object_store.add_pack_data(count, pack_data, progress) return self.get_refs() def fetch_pack_data(self, determine_wants, graph_walker, progress, get_tagged=None, depth=None): """Fetch the pack data required for a set of revisions. Args: determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. progress: Simple progress function that will be called with updated progress strings. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. depth: Shallow fetch depth Returns: count and iterator over pack data """ # TODO(jelmer): Fetch pack data directly, don't create objects first. objects = self.fetch_objects(determine_wants, graph_walker, progress, get_tagged, depth=depth) return pack_objects_to_data(objects) def fetch_objects(self, determine_wants, graph_walker, progress, get_tagged=None, depth=None): """Fetch the missing objects required for a set of revisions. Args: determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. progress: Simple progress function that will be called with updated progress strings. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. depth: Shallow fetch depth Returns: iterator over objects, with __len__ implemented """ if depth not in (None, 0): raise NotImplementedError("depth not supported yet") refs = {} for ref, sha in self.get_refs().items(): try: obj = self.object_store[sha] except KeyError: warnings.warn( 'ref %s points at non-present sha %s' % ( ref.decode('utf-8', 'replace'), sha.decode('ascii')), UserWarning) continue else: if isinstance(obj, Tag): refs[ref + ANNOTATED_TAG_SUFFIX] = obj.object[1] refs[ref] = sha wants = determine_wants(refs) if not isinstance(wants, list): raise TypeError("determine_wants() did not return a list") shallows = getattr(graph_walker, 'shallow', frozenset()) unshallows = getattr(graph_walker, 'unshallow', frozenset()) if wants == []: # TODO(dborowitz): find a way to short-circuit that doesn't change # this interface. if shallows or unshallows: # Do not send a pack in shallow short-circuit path return None return [] # If the graph walker is set up with an implementation that can # ACK/NAK to the wire, it will write data to the client through # this call as a side-effect. haves = self.object_store.find_common_revisions(graph_walker) # Deal with shallow requests separately because the haves do # not reflect what objects are missing if shallows or unshallows: # TODO: filter the haves commits from iter_shas. the specific # commits aren't missing. haves = [] def get_parents(commit): if commit.id in shallows: return [] return self.get_parents(commit.id, commit) return self.object_store.iter_shas( self.object_store.find_missing_objects( haves, wants, self.get_shallow(), progress, get_tagged, get_parents=get_parents)) def generate_pack_data(self, have, want, progress=None, ofs_delta=None): """Generate pack data objects for a set of wants/haves. Args: have: List of SHA1s of objects that should not be sent want: List of SHA1s of objects that should be sent ofs_delta: Whether OFS deltas can be included progress: Optional progress reporting method """ return self.object_store.generate_pack_data( have, want, shallow=self.get_shallow(), progress=progress, ofs_delta=ofs_delta) def get_graph_walker(self, heads=None): """Retrieve a graph walker. A graph walker is used by a remote repository (or proxy) to find out which objects are present in this repository. Args: heads: Repository heads to use (optional) Returns: A graph walker object """ if heads is None: heads = [ sha for sha in self.refs.as_dict(b'refs/heads').values() if sha in self.object_store] return ObjectStoreGraphWalker( heads, self.get_parents, shallow=self.get_shallow()) def get_refs(self): """Get dictionary with all refs. Returns: A ``dict`` mapping ref names to SHA1s """ return self.refs.as_dict() def head(self): """Return the SHA1 pointed at by HEAD.""" return self.refs[b'HEAD'] def _get_object(self, sha, cls): assert len(sha) in (20, 40) ret = self.get_object(sha) if not isinstance(ret, cls): if cls is Commit: raise NotCommitError(ret) elif cls is Blob: raise NotBlobError(ret) elif cls is Tree: raise NotTreeError(ret) elif cls is Tag: raise NotTagError(ret) else: raise Exception("Type invalid: %r != %r" % ( ret.type_name, cls.type_name)) return ret def get_object(self, sha): """Retrieve the object with the specified SHA. Args: sha: SHA to retrieve Returns: A ShaFile object Raises: KeyError: when the object can not be found """ return self.object_store[sha] def get_parents(self, sha, commit=None): """Retrieve the parents of a specific commit. If the specific commit is a graftpoint, the graft parents will be returned instead. Args: sha: SHA of the commit for which to retrieve the parents commit: Optional commit matching the sha Returns: List of parents """ try: return self._graftpoints[sha] except KeyError: if commit is None: commit = self[sha] return commit.parents def get_config(self): """Retrieve the config object. Returns: `ConfigFile` object for the ``.git/config`` file. """ raise NotImplementedError(self.get_config) def get_description(self): """Retrieve the description for this repository. Returns: String with the description of the repository as set by the user. """ raise NotImplementedError(self.get_description) def set_description(self, description): """Set the description for this repository. Args: description: Text to set as description for this repository. """ raise NotImplementedError(self.set_description) def get_config_stack(self): """Return a config stack for this repository. This stack accesses the configuration for both this repository itself (.git/config) and the global configuration, which usually lives in ~/.gitconfig. Returns: `Config` instance for this repository """ from dulwich.config import StackedConfig backends = [self.get_config()] + StackedConfig.default_backends() return StackedConfig(backends, writable=backends[0]) def get_shallow(self): """Get the set of shallow commits. Returns: Set of shallow commits. """ f = self.get_named_file('shallow') if f is None: return set() with f: return set(l.strip() for l in f) def update_shallow(self, new_shallow, new_unshallow): """Update the list of shallow objects. Args: new_shallow: Newly shallow objects new_unshallow: Newly no longer shallow objects """ shallow = self.get_shallow() if new_shallow: shallow.update(new_shallow) if new_unshallow: shallow.difference_update(new_unshallow) self._put_named_file( 'shallow', b''.join([sha + b'\n' for sha in shallow])) def get_peeled(self, ref): """Get the peeled value of a ref. Args: ref: The refname to peel. Returns: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ cached = self.refs.get_peeled(ref) if cached is not None: return cached return self.object_store.peel_sha(self.refs[ref]).id def get_walker(self, include=None, *args, **kwargs): """Obtain a walker for this repository. Args: include: Iterable of SHAs of commits to include along with their ancestors. Defaults to [HEAD] exclude: Iterable of SHAs of commits to exclude along with their ancestors, overriding includes. order: ORDER_* constant specifying the order of results. Anything other than ORDER_DATE may result in O(n) memory usage. reverse: If True, reverse the order of output, requiring O(n) memory. max_entries: The maximum number of entries to yield, or None for no limit. paths: Iterable of file or subtree paths to show entries for. rename_detector: diff.RenameDetector object for detecting renames. follow: If True, follow path across renames/copies. Forces a default rename_detector. since: Timestamp to list commits after. until: Timestamp to list commits before. queue_cls: A class to use for a queue of commits, supporting the iterator protocol. The constructor takes a single argument, the Walker. Returns: A `Walker` object """ from dulwich.walk import Walker if include is None: include = [self.head()] if isinstance(include, str): include = [include] kwargs['get_parents'] = lambda commit: self.get_parents( commit.id, commit) return Walker(self.object_store, include, *args, **kwargs) def __getitem__(self, name): """Retrieve a Git object by SHA1 or ref. Args: name: A Git object SHA1 or a ref name Returns: A `ShaFile` object, such as a Commit or Blob Raises: KeyError: when the specified ref or object does not exist """ if not isinstance(name, bytes): raise TypeError("'name' must be bytestring, not %.80s" % type(name).__name__) if len(name) in (20, 40): try: return self.object_store[name] except (KeyError, ValueError): pass try: return self.object_store[self.refs[name]] except RefFormatError: raise KeyError(name) def __contains__(self, name): """Check if a specific Git object or ref is present. Args: name: Git object SHA1 or ref name """ if len(name) in (20, 40): return name in self.object_store or name in self.refs else: return name in self.refs def __setitem__(self, name, value): """Set a ref. Args: name: ref name value: Ref value - either a ShaFile object, or a hex sha """ if name.startswith(b"refs/") or name == b'HEAD': if isinstance(value, ShaFile): self.refs[name] = value.id elif isinstance(value, bytes): self.refs[name] = value else: raise TypeError(value) else: raise ValueError(name) def __delitem__(self, name): """Remove a ref. Args: name: Name of the ref to remove """ if name.startswith(b"refs/") or name == b"HEAD": del self.refs[name] else: raise ValueError(name) def _get_user_identity(self, config, kind=None): """Determine the identity to use for new commits. """ # TODO(jelmer): Deprecate this function in favor of get_user_identity return get_user_identity(config) def _add_graftpoints(self, updated_graftpoints): """Add or modify graftpoints Args: updated_graftpoints: Dict of commit shas to list of parent shas """ # Simple validation for commit, parents in updated_graftpoints.items(): for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') self._graftpoints.update(updated_graftpoints) def _remove_graftpoints(self, to_remove=[]): """Remove graftpoints Args: to_remove: List of commit shas """ for sha in to_remove: del self._graftpoints[sha] def _read_heads(self, name): f = self.get_named_file(name) if f is None: return [] with f: return [l.strip() for l in f.readlines() if l.strip()] def do_commit(self, message=None, committer=None, author=None, commit_timestamp=None, commit_timezone=None, author_timestamp=None, author_timezone=None, tree=None, encoding=None, ref=b'HEAD', merge_heads=None): """Create a new commit. Args: message: Commit message committer: Committer fullname author: Author fullname (defaults to committer) commit_timestamp: Commit timestamp (defaults to now) commit_timezone: Commit timestamp timezone (defaults to GMT) author_timestamp: Author timestamp (defaults to commit timestamp) author_timezone: Author timestamp timezone (defaults to commit timestamp timezone) tree: SHA1 of the tree root to use (if not specified the current index will be committed). encoding: Encoding ref: Optional ref to commit to (defaults to current branch) merge_heads: Merge heads (defaults to .git/MERGE_HEADS) Returns: New commit SHA1 """ import time c = Commit() if tree is None: index = self.open_index() c.tree = index.commit(self.object_store) else: if len(tree) != 40: raise ValueError("tree must be a 40-byte hex sha string") c.tree = tree try: self.hooks['pre-commit'].execute() except HookError as e: raise CommitError(e) except KeyError: # no hook defined, silent fallthrough pass config = self.get_config_stack() if merge_heads is None: merge_heads = self._read_heads('MERGE_HEADS') if committer is None: committer = get_user_identity(config, kind='COMMITTER') check_user_identity(committer) c.committer = committer if commit_timestamp is None: # FIXME: Support GIT_COMMITTER_DATE environment variable commit_timestamp = time.time() c.commit_time = int(commit_timestamp) if commit_timezone is None: # FIXME: Use current user timezone rather than UTC commit_timezone = 0 c.commit_timezone = commit_timezone if author is None: author = get_user_identity(config, kind='AUTHOR') c.author = author check_user_identity(author) if author_timestamp is None: # FIXME: Support GIT_AUTHOR_DATE environment variable author_timestamp = commit_timestamp c.author_time = int(author_timestamp) if author_timezone is None: author_timezone = commit_timezone c.author_timezone = author_timezone if encoding is None: try: encoding = config.get(('i18n', ), 'commitEncoding') except KeyError: pass # No dice if encoding is not None: c.encoding = encoding if message is None: # FIXME: Try to read commit message from .git/MERGE_MSG raise ValueError("No commit message specified") try: c.message = self.hooks['commit-msg'].execute(message) if c.message is None: c.message = message except HookError as e: raise CommitError(e) except KeyError: # no hook defined, message not modified c.message = message if ref is None: # Create a dangling commit c.parents = merge_heads self.object_store.add_object(c) else: try: old_head = self.refs[ref] c.parents = [old_head] + merge_heads self.object_store.add_object(c) ok = self.refs.set_if_equals( ref, old_head, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) except KeyError: c.parents = merge_heads self.object_store.add_object(c) ok = self.refs.add_if_new( ref, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) if not ok: # Fail if the atomic compare-and-swap failed, leaving the # commit and all its objects as garbage. raise CommitError("%s changed during commit" % (ref,)) self._del_named_file('MERGE_HEADS') try: self.hooks['post-commit'].execute() except HookError as e: # silent failure warnings.warn("post-commit hook failed: %s" % e, UserWarning) except KeyError: # no hook defined, silent fallthrough pass return c.id def read_gitfile(f): """Read a ``.git`` file. The first line of the file should start with "gitdir: " Args: f: File-like object to read from Returns: A path """ cs = f.read() if not cs.startswith("gitdir: "): raise ValueError("Expected file to start with 'gitdir: '") return cs[len("gitdir: "):].rstrip("\n") class Repo(BaseRepo): """A git repository backed by local disk. To open an existing repository, call the contructor with the path of the repository. To create a new repository, use the Repo.init class method. """ def __init__(self, root): hidden_path = os.path.join(root, CONTROLDIR) if os.path.isdir(os.path.join(hidden_path, OBJECTDIR)): self.bare = False self._controldir = hidden_path elif (os.path.isdir(os.path.join(root, OBJECTDIR)) and os.path.isdir(os.path.join(root, REFSDIR))): self.bare = True self._controldir = root elif os.path.isfile(hidden_path): self.bare = False with open(hidden_path, 'r') as f: path = read_gitfile(f) self.bare = False self._controldir = os.path.join(root, path) else: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=root) ) commondir = self.get_named_file(COMMONDIR) if commondir is not None: with commondir: self._commondir = os.path.join( self.controldir(), - commondir.read().rstrip(b"\r\n").decode( - sys.getfilesystemencoding())) + os.fsdecode(commondir.read().rstrip(b"\r\n"))) else: self._commondir = self._controldir self.path = root config = self.get_config() object_store = DiskObjectStore.from_config( os.path.join(self.commondir(), OBJECTDIR), config) refs = DiskRefsContainer(self.commondir(), self._controldir, logger=self._write_reflog) BaseRepo.__init__(self, object_store, refs) self._graftpoints = {} graft_file = self.get_named_file(os.path.join("info", "grafts"), basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) graft_file = self.get_named_file("shallow", basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) self.hooks['pre-commit'] = PreCommitShellHook(self.controldir()) self.hooks['commit-msg'] = CommitMsgShellHook(self.controldir()) self.hooks['post-commit'] = PostCommitShellHook(self.controldir()) self.hooks['post-receive'] = PostReceiveShellHook(self.controldir()) def _write_reflog(self, ref, old_sha, new_sha, committer, timestamp, timezone, message): from .reflog import format_reflog_line - path = os.path.join( - self.controldir(), 'logs', - ref.decode(sys.getfilesystemencoding())) + path = os.path.join(self.controldir(), 'logs', os.fsdecode(ref)) try: os.makedirs(os.path.dirname(path)) except OSError as e: if e.errno != errno.EEXIST: raise if committer is None: config = self.get_config_stack() committer = self._get_user_identity(config) check_user_identity(committer) if timestamp is None: timestamp = int(time.time()) if timezone is None: timezone = 0 # FIXME with open(path, 'ab') as f: f.write(format_reflog_line(old_sha, new_sha, committer, timestamp, timezone, message) + b'\n') @classmethod def discover(cls, start='.'): """Iterate parent directories to discover a repository Return a Repo object for the first parent directory that looks like a Git repository. Args: start: The directory to start discovery from (defaults to '.') """ remaining = True path = os.path.abspath(start) while remaining: try: return cls(path) except NotGitRepository: path, remaining = os.path.split(path) raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=start) ) def controldir(self): """Return the path of the control directory.""" return self._controldir def commondir(self): """Return the path of the common directory. For a main working tree, it is identical to controldir(). For a linked working tree, it is the control directory of the main working tree.""" return self._commondir def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ fname = os.path.join(self.path, '.probe-permissions') with open(fname, 'w') as f: f.write('') st1 = os.lstat(fname) try: os.chmod(fname, st1.st_mode ^ stat.S_IXUSR) except EnvironmentError as e: if e.errno == errno.EPERM: return False raise st2 = os.lstat(fname) os.unlink(fname) mode_differs = st1.st_mode != st2.st_mode st2_has_exec = (st2.st_mode & stat.S_IXUSR) != 0 return mode_differs and st2_has_exec def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ path = path.lstrip(os.path.sep) with GitFile(os.path.join(self.controldir(), path), 'wb') as f: f.write(contents) def _del_named_file(self, path): try: os.unlink(os.path.join(self.controldir(), path)) except (IOError, OSError) as e: if e.errno == errno.ENOENT: return raise def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. basedir: Optional argument that specifies an alternative to the control dir. Returns: An open file object, or None if the file does not exist. """ # TODO(dborowitz): sanitize filenames, since this is used directly by # the dumb web serving code. if basedir is None: basedir = self.controldir() path = path.lstrip(os.path.sep) try: return open(os.path.join(basedir, path), 'rb') except (IOError, OSError) as e: if e.errno == errno.ENOENT: return None raise def index_path(self): """Return path to the index file.""" return os.path.join(self.controldir(), INDEX_FILENAME) def open_index(self): """Open the index for this repository. Raises: NoIndexPresent: If no index is present Returns: The matching `Index` """ from dulwich.index import Index if not self.has_index(): raise NoIndexPresent() return Index(self.index_path()) def has_index(self): """Check if an index is present.""" # Bare repos must never have index files; non-bare repos may have a # missing index file, which is treated as empty. return not self.bare def stage(self, fs_paths): """Stage a set of paths. Args: fs_paths: List of paths, relative to the repository path """ - root_path_bytes = self.path.encode(sys.getfilesystemencoding()) + root_path_bytes = os.fsencode(self.path) if not isinstance(fs_paths, list): fs_paths = [fs_paths] from dulwich.index import ( blob_from_path_and_stat, index_entry_from_stat, _fs_to_tree_path, ) index = self.open_index() blob_normalizer = self.get_blob_normalizer() for fs_path in fs_paths: if not isinstance(fs_path, bytes): - fs_path = fs_path.encode(sys.getfilesystemencoding()) + fs_path = os.fsencode(fs_path) if os.path.isabs(fs_path): raise ValueError( "path %r should be relative to " "repository root, not absolute" % fs_path) tree_path = _fs_to_tree_path(fs_path) full_path = os.path.join(root_path_bytes, fs_path) try: st = os.lstat(full_path) except OSError: # File no longer exists try: del index[tree_path] except KeyError: pass # already removed else: if (not stat.S_ISREG(st.st_mode) and not stat.S_ISLNK(st.st_mode)): try: del index[tree_path] except KeyError: pass else: blob = blob_from_path_and_stat(full_path, st) blob = blob_normalizer.checkin_normalize(blob, fs_path) self.object_store.add_object(blob) index[tree_path] = index_entry_from_stat(st, blob.id, 0) index.write() def clone(self, target_path, mkdir=True, bare=False, origin=b"origin", checkout=None): """Clone this repository. Args: target_path: Target path mkdir: Create the target directory bare: Whether to create a bare repository origin: Base name for refs in target repository cloned from this repository Returns: Created repository as `Repo` """ if not bare: target = self.init(target_path, mkdir=mkdir) else: if checkout: raise ValueError("checkout and bare are incompatible") target = self.init_bare(target_path, mkdir=mkdir) self.fetch(target) encoded_path = self.path if not isinstance(encoded_path, bytes): - encoded_path = encoded_path.encode(sys.getfilesystemencoding()) + encoded_path = os.fsencode(encoded_path) ref_message = b"clone: from " + encoded_path target.refs.import_refs( b'refs/remotes/' + origin, self.refs.as_dict(b'refs/heads'), message=ref_message) target.refs.import_refs( b'refs/tags', self.refs.as_dict(b'refs/tags'), message=ref_message) try: target.refs.add_if_new( DEFAULT_REF, self.refs[DEFAULT_REF], message=ref_message) except KeyError: pass target_config = target.get_config() target_config.set(('remote', 'origin'), 'url', encoded_path) target_config.set(('remote', 'origin'), 'fetch', '+refs/heads/*:refs/remotes/origin/*') target_config.write_to_path() # Update target head head_chain, head_sha = self.refs.follow(b'HEAD') if head_chain and head_sha is not None: target.refs.set_symbolic_ref(b'HEAD', head_chain[-1], message=ref_message) target[b'HEAD'] = head_sha if checkout is None: checkout = (not bare) if checkout: # Checkout HEAD to target dir target.reset_index() return target def reset_index(self, tree=None): """Reset the index back to a specific tree. Args: tree: Tree SHA to reset to, None for current HEAD tree. """ from dulwich.index import ( build_index_from_tree, validate_path_element_default, validate_path_element_ntfs, ) if tree is None: tree = self[b'HEAD'].tree config = self.get_config() honor_filemode = config.get_boolean( b'core', b'filemode', os.name != "nt") if config.get_boolean(b'core', b'core.protectNTFS', os.name == "nt"): validate_path_element = validate_path_element_ntfs else: validate_path_element = validate_path_element_default return build_index_from_tree( self.path, self.index_path(), self.object_store, tree, honor_filemode=honor_filemode, validate_path_element=validate_path_element) def get_config(self): """Retrieve the config object. Returns: `ConfigFile` object for the ``.git/config`` file. """ from dulwich.config import ConfigFile path = os.path.join(self._controldir, 'config') try: return ConfigFile.from_path(path) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise ret = ConfigFile() ret.path = path return ret def get_description(self): """Retrieve the description of this repository. Returns: A string describing the repository or None. """ path = os.path.join(self._controldir, 'description') try: with GitFile(path, 'rb') as f: return f.read() except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise return None def __repr__(self): return "" % self.path def set_description(self, description): """Set the description for this repository. Args: description: Text to set as description for this repository. """ self._put_named_file('description', description) @classmethod def _init_maybe_bare(cls, path, bare): for d in BASE_DIRECTORIES: os.mkdir(os.path.join(path, *d)) DiskObjectStore.init(os.path.join(path, OBJECTDIR)) ret = cls(path) ret.refs.set_symbolic_ref(b'HEAD', DEFAULT_REF) ret._init_files(bare) return ret @classmethod def init(cls, path, mkdir=False): """Create a new repository. Args: path: Path in which to create the repository mkdir: Whether to create the directory Returns: `Repo` instance """ if mkdir: os.mkdir(path) controldir = os.path.join(path, CONTROLDIR) os.mkdir(controldir) _set_filesystem_hidden(controldir) cls._init_maybe_bare(controldir, False) return cls(path) @classmethod def _init_new_working_directory(cls, path, main_repo, identifier=None, mkdir=False): """Create a new working directory linked to a repository. Args: path: Path in which to create the working tree. main_repo: Main repository to reference identifier: Worktree identifier mkdir: Whether to create the directory Returns: `Repo` instance """ if mkdir: os.mkdir(path) if identifier is None: identifier = os.path.basename(path) main_worktreesdir = os.path.join(main_repo.controldir(), WORKTREES) worktree_controldir = os.path.join(main_worktreesdir, identifier) gitdirfile = os.path.join(path, CONTROLDIR) with open(gitdirfile, 'wb') as f: - f.write(b'gitdir: ' + - worktree_controldir.encode(sys.getfilesystemencoding()) + - b'\n') + f.write(b'gitdir: ' + os.fsencode(worktree_controldir) + b'\n') try: os.mkdir(main_worktreesdir) except OSError as e: if e.errno != errno.EEXIST: raise try: os.mkdir(worktree_controldir) except OSError as e: if e.errno != errno.EEXIST: raise with open(os.path.join(worktree_controldir, GITDIR), 'wb') as f: - f.write(gitdirfile.encode(sys.getfilesystemencoding()) + b'\n') + f.write(os.fsencode(gitdirfile) + b'\n') with open(os.path.join(worktree_controldir, COMMONDIR), 'wb') as f: f.write(b'../..\n') with open(os.path.join(worktree_controldir, 'HEAD'), 'wb') as f: f.write(main_repo.head() + b'\n') r = cls(path) r.reset_index() return r @classmethod def init_bare(cls, path, mkdir=False): """Create a new bare repository. ``path`` should already exist and be an empty directory. Args: path: Path to create bare repository in Returns: a `Repo` instance """ if mkdir: os.mkdir(path) return cls._init_maybe_bare(path, True) create = init_bare def close(self): """Close any files opened by this repository.""" self.object_store.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def get_blob_normalizer(self): """ Return a BlobNormalizer object """ # TODO Parse the git attributes files git_attributes = {} return BlobNormalizer( self.get_config_stack(), git_attributes ) class MemoryRepo(BaseRepo): """Repo that stores refs, objects, and named files in memory. MemoryRepos are always bare: they have no working tree and no index, since those have a stronger dependency on the filesystem. """ def __init__(self): from dulwich.config import ConfigFile self._reflog = [] refs_container = DictRefsContainer({}, logger=self._append_reflog) BaseRepo.__init__(self, MemoryObjectStore(), refs_container) self._named_files = {} self.bare = True self._config = ConfigFile() self._description = None def _append_reflog(self, *args): self._reflog.append(args) def set_description(self, description): self._description = description def get_description(self): return self._description def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ return sys.platform != 'win32' def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ self._named_files[path] = contents def _del_named_file(self, path): try: del self._named_files[path] except KeyError: pass def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-baked Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. Returns: An open file object, or None if the file does not exist. """ contents = self._named_files.get(path, None) if contents is None: return None return BytesIO(contents) def open_index(self): """Fail to open index for this repo, since it is bare. Raises: NoIndexPresent: Raised when no index is present """ raise NoIndexPresent() def get_config(self): """Retrieve the config object. Returns: `ConfigFile` object. """ return self._config @classmethod def init_bare(cls, objects, refs): """Create a new bare repository in memory. Args: objects: Objects for the new repository, as iterable refs: Refs as dictionary, mapping names to object SHA1s """ ret = cls() for obj in objects: ret.object_store.add_object(obj) for refname, sha in refs.items(): ret.refs.add_if_new(refname, sha) ret._init_files(bare=True) return ret diff --git a/dulwich/server.py b/dulwich/server.py index 29313aff..6d490d73 100644 --- a/dulwich/server.py +++ b/dulwich/server.py @@ -1,1211 +1,1211 @@ # server.py -- Implementation of the server side git protocols # Copyright (C) 2008 John Carr # Coprygith (C) 2011-2012 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. # """Git smart network protocol server implementation. For more detailed implementation on the network protocol, see the Documentation/technical directory in the cgit distribution, and in particular: * Documentation/technical/protocol-capabilities.txt * Documentation/technical/pack-protocol.txt Currently supported capabilities: * include-tag * thin-pack * multi_ack_detailed * multi_ack * side-band-64k * ofs-delta * no-progress * report-status * delete-refs * shallow * symref """ import collections import os import socket import sys import time import zlib import socketserver from dulwich.archive import tar_stream from dulwich.errors import ( ApplyDeltaError, ChecksumMismatch, GitProtocolError, HookError, NotGitRepository, UnexpectedCommandError, ObjectFormatException, ) from dulwich import log_utils from dulwich.objects import ( Commit, valid_hexsha, ) from dulwich.pack import ( write_pack_objects, ) from dulwich.protocol import ( # noqa: F401 BufferedPktLineWriter, capability_agent, CAPABILITIES_REF, CAPABILITY_DELETE_REFS, CAPABILITY_INCLUDE_TAG, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_NO_DONE, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, CAPABILITY_SHALLOW, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, COMMAND_DEEPEN, COMMAND_DONE, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW, COMMAND_WANT, MULTI_ACK, MULTI_ACK_DETAILED, Protocol, ProtocolFile, ReceivableProtocol, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, SINGLE_ACK, TCP_GIT_PORT, ZERO_SHA, ack_type, extract_capabilities, extract_want_line_capabilities, symref_capabilities, ) from dulwich.refs import ( ANNOTATED_TAG_SUFFIX, write_info_refs, ) from dulwich.repo import ( Repo, ) logger = log_utils.getLogger(__name__) class Backend(object): """A backend for the Git smart server implementation.""" def open_repository(self, path): """Open the repository at a path. Args: path: Path to the repository Raises: NotGitRepository: no git repository was found at path Returns: Instance of BackendRepo """ raise NotImplementedError(self.open_repository) class BackendRepo(object): """Repository abstraction used by the Git server. The methods required here are a subset of those provided by dulwich.repo.Repo. """ object_store = None refs = None def get_refs(self): """ Get all the refs in the repository Returns: dict of name -> sha """ raise NotImplementedError def get_peeled(self, name): """Return the cached peeled value of a ref, if available. Args: name: Name of the ref to peel Returns: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If no cached information about a tag is available, this method may return None, but it should attempt to peel the tag if possible. """ return None def fetch_objects(self, determine_wants, graph_walker, progress, get_tagged=None): """ Yield the objects required for a list of commits. Args: progress: is a callback to send progress messages to the client get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. """ raise NotImplementedError class DictBackend(Backend): """Trivial backend that looks up Git repositories in a dictionary.""" def __init__(self, repos): self.repos = repos def open_repository(self, path): logger.debug('Opening repository at %s', path) try: return self.repos[path] except KeyError: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=path) ) class FileSystemBackend(Backend): """Simple backend looking up Git repositories in the local file system.""" def __init__(self, root=os.sep): super(FileSystemBackend, self).__init__() self.root = (os.path.abspath(root) + os.sep).replace( os.sep * 2, os.sep) def open_repository(self, path): logger.debug('opening repository at %s', path) abspath = os.path.abspath(os.path.join(self.root, path)) + os.sep normcase_abspath = os.path.normcase(abspath) normcase_root = os.path.normcase(self.root) if not normcase_abspath.startswith(normcase_root): raise NotGitRepository( "Path %r not inside root %r" % (path, self.root)) return Repo(abspath) class Handler(object): """Smart protocol command handler base class.""" def __init__(self, backend, proto, http_req=None): self.backend = backend self.proto = proto self.http_req = http_req def handle(self): raise NotImplementedError(self.handle) class PackHandler(Handler): """Protocol handler for packs.""" def __init__(self, backend, proto, http_req=None): super(PackHandler, self).__init__(backend, proto, http_req) self._client_capabilities = None # Flags needed for the no-done capability self._done_received = False @classmethod def capability_line(cls, capabilities): logger.info('Sending capabilities: %s', capabilities) return b"".join([b" " + c for c in capabilities]) @classmethod def capabilities(cls): raise NotImplementedError(cls.capabilities) @classmethod def innocuous_capabilities(cls): return [CAPABILITY_INCLUDE_TAG, CAPABILITY_THIN_PACK, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA, capability_agent()] @classmethod def required_capabilities(cls): """Return a list of capabilities that we require the client to have.""" return [] def set_client_capabilities(self, caps): allowable_caps = set(self.innocuous_capabilities()) allowable_caps.update(self.capabilities()) for cap in caps: if cap not in allowable_caps: raise GitProtocolError('Client asked for capability %s that ' 'was not advertised.' % cap) for cap in self.required_capabilities(): if cap not in caps: raise GitProtocolError('Client does not support required ' 'capability %s.' % cap) self._client_capabilities = set(caps) logger.info('Client capabilities: %s', caps) def has_capability(self, cap): if self._client_capabilities is None: raise GitProtocolError('Server attempted to access capability %s ' 'before asking client' % cap) return cap in self._client_capabilities def notify_done(self): self._done_received = True class UploadPackHandler(PackHandler): """Protocol handler for uploading a pack to the client.""" def __init__(self, backend, args, proto, http_req=None, advertise_refs=False): super(UploadPackHandler, self).__init__( backend, proto, http_req=http_req) self.repo = backend.open_repository(args[0]) self._graph_walker = None self.advertise_refs = advertise_refs # A state variable for denoting that the have list is still # being processed, and the client is not accepting any other # data (such as side-band, see the progress method here). self._processing_have_lines = False @classmethod def capabilities(cls): return [CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA, CAPABILITY_NO_PROGRESS, CAPABILITY_INCLUDE_TAG, CAPABILITY_SHALLOW, CAPABILITY_NO_DONE] @classmethod def required_capabilities(cls): return (CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA) def progress(self, message): if (self.has_capability(CAPABILITY_NO_PROGRESS) or self._processing_have_lines): return self.proto.write_sideband(SIDE_BAND_CHANNEL_PROGRESS, message) def get_tagged(self, refs=None, repo=None): """Get a dict of peeled values of tags to their original tag shas. Args: refs: dict of refname -> sha of possible tags; defaults to all of the backend's refs. repo: optional Repo instance for getting peeled refs; defaults to the backend's repo, if available Returns: dict of peeled_sha -> tag_sha, where tag_sha is the sha of a tag whose peeled value is peeled_sha. """ if not self.has_capability(CAPABILITY_INCLUDE_TAG): return {} if refs is None: refs = self.repo.get_refs() if repo is None: repo = getattr(self.repo, "repo", None) if repo is None: # Bail if we don't have a Repo available; this is ok since # clients must be able to handle if the server doesn't include # all relevant tags. # TODO: fix behavior when missing return {} # TODO(jelmer): Integrate this with the refs logic in # Repo.fetch_objects tagged = {} for name, sha in refs.items(): peeled_sha = repo.get_peeled(name) if peeled_sha != sha: tagged[peeled_sha] = sha return tagged def handle(self): def write(x): return self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, x) graph_walker = _ProtocolGraphWalker( self, self.repo.object_store, self.repo.get_peeled, self.repo.refs.get_symrefs) objects_iter = self.repo.fetch_objects( graph_walker.determine_wants, graph_walker, self.progress, get_tagged=self.get_tagged) # Note the fact that client is only processing responses related # to the have lines it sent, and any other data (including side- # band) will be be considered a fatal error. self._processing_have_lines = True # 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. # Also, if it also happens that the object_iter is instantiated # with a graph walker with an implementation that talks over the # wire (which is this instance of this class) this will actually # iterate through everything and write things out to the wire. if len(objects_iter) == 0: return # The provided haves are processed, and it is safe to send side- # band data now. self._processing_have_lines = False if not graph_walker.handle_done( not self.has_capability(CAPABILITY_NO_DONE), self._done_received): return self.progress( ("counting objects: %d, done.\n" % len(objects_iter)).encode( 'ascii')) write_pack_objects(ProtocolFile(None, write), objects_iter) # we are done self.proto.write_pkt_line(None) def _split_proto_line(line, allowed): """Split a line read from the wire. Args: line: The line read from the wire. allowed: An iterable of command names that should be allowed. Command names not listed below as possible return values will be ignored. If None, any commands from the possible return values are allowed. Returns: a tuple having one of the following forms: ('want', obj_id) ('have', obj_id) ('done', None) (None, None) (for a flush-pkt) Raises: UnexpectedCommandError: if the line cannot be parsed into one of the allowed return values. """ if not line: fields = [None] else: fields = line.rstrip(b'\n').split(b' ', 1) command = fields[0] if allowed is not None and command not in allowed: raise UnexpectedCommandError(command) if len(fields) == 1 and command in (COMMAND_DONE, None): return (command, None) elif len(fields) == 2: if command in (COMMAND_WANT, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW): if not valid_hexsha(fields[1]): raise GitProtocolError("Invalid sha") return tuple(fields) elif command == COMMAND_DEEPEN: return command, int(fields[1]) raise GitProtocolError('Received invalid line from client: %r' % line) def _find_shallow(store, heads, depth): """Find shallow commits according to a given depth. Args: store: An ObjectStore for looking up objects. heads: Iterable of head SHAs to start walking from. depth: The depth of ancestors to include. A depth of one includes only the heads themselves. Returns: A tuple of (shallow, not_shallow), sets of SHAs that should be considered shallow and unshallow according to the arguments. Note that these sets may overlap if a commit is reachable along multiple paths. """ parents = {} def get_parents(sha): result = parents.get(sha, None) if not result: result = store[sha].parents parents[sha] = result return result todo = [] # stack of (sha, depth) for head_sha in heads: obj = store.peel_sha(head_sha) if isinstance(obj, Commit): todo.append((obj.id, 1)) not_shallow = set() shallow = set() while todo: sha, cur_depth = todo.pop() if cur_depth < depth: not_shallow.add(sha) new_depth = cur_depth + 1 todo.extend((p, new_depth) for p in get_parents(sha)) else: shallow.add(sha) return shallow, not_shallow def _want_satisfied(store, haves, want, earliest): o = store[want] pending = collections.deque([o]) known = set([want]) while pending: commit = pending.popleft() if commit.id in haves: return True if commit.type_name != b"commit": # non-commit wants are assumed to be satisfied continue for parent in commit.parents: if parent in known: continue known.add(parent) parent_obj = store[parent] # TODO: handle parents with later commit times than children if parent_obj.commit_time >= earliest: pending.append(parent_obj) return False def _all_wants_satisfied(store, haves, wants): """Check whether all the current wants are satisfied by a set of haves. Args: store: Object store to retrieve objects from haves: A set of commits we know the client has. wants: A set of commits the client wants Note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ haves = set(haves) if haves: earliest = min([store[h].commit_time for h in haves]) else: earliest = 0 for want in wants: if not _want_satisfied(store, haves, want, earliest): return False return True class _ProtocolGraphWalker(object): """A graph walker that knows the git protocol. As a graph walker, this class implements ack(), next(), and reset(). It also contains some base methods for interacting with the wire and walking the commit tree. The work of determining which acks to send is passed on to the implementation instance stored in _impl. The reason for this is that we do not know at object creation time what ack level the protocol requires. A call to set_ack_type() is required to set up the implementation, before any calls to next() or ack() are made. """ def __init__(self, handler, object_store, get_peeled, get_symrefs): self.handler = handler self.store = object_store self.get_peeled = get_peeled self.get_symrefs = get_symrefs self.proto = handler.proto self.http_req = handler.http_req self.advertise_refs = handler.advertise_refs self._wants = [] self.shallow = set() self.client_shallow = set() self.unshallow = set() self._cached = False self._cache = [] self._cache_index = 0 self._impl = None def determine_wants(self, heads): """Determine the wants for a set of heads. The given heads are advertised to the client, who then specifies which refs he wants using 'want' lines. This portion of the protocol is the same regardless of ack type, and in fact is used to set the ack type of the ProtocolGraphWalker. If the client has the 'shallow' capability, this method also reads and responds to the 'shallow' and 'deepen' lines from the client. These are not part of the wants per se, but they set up necessary state for walking the graph. Additionally, later code depends on this method consuming everything up to the first 'have' line. Args: heads: a dict of refname->SHA1 to advertise Returns: a list of SHA1s requested by the client """ symrefs = self.get_symrefs() values = set(heads.values()) if self.advertise_refs or not self.http_req: for i, (ref, sha) in enumerate(sorted(heads.items())): try: peeled_sha = self.get_peeled(ref) except KeyError: # Skip refs that are inaccessible # TODO(jelmer): Integrate with Repo.fetch_objects refs # logic. continue line = sha + b' ' + ref if not i: line += (b'\x00' + self.handler.capability_line( self.handler.capabilities() + symref_capabilities(symrefs.items()))) self.proto.write_pkt_line(line + b'\n') if peeled_sha != sha: self.proto.write_pkt_line( peeled_sha + b' ' + ref + ANNOTATED_TAG_SUFFIX + b'\n') # i'm done.. self.proto.write_pkt_line(None) if self.advertise_refs: return [] # Now client will sending want want want commands want = self.proto.read_pkt_line() if not want: return [] line, caps = extract_want_line_capabilities(want) self.handler.set_client_capabilities(caps) self.set_ack_type(ack_type(caps)) allowed = (COMMAND_WANT, COMMAND_SHALLOW, COMMAND_DEEPEN, None) command, sha = _split_proto_line(line, allowed) want_revs = [] while command == COMMAND_WANT: if sha not in values: raise GitProtocolError( 'Client wants invalid object %s' % sha) want_revs.append(sha) command, sha = self.read_proto_line(allowed) self.set_wants(want_revs) if command in (COMMAND_SHALLOW, COMMAND_DEEPEN): self.unread_proto_line(command, sha) self._handle_shallow_request(want_revs) if self.http_req and self.proto.eof(): # The client may close the socket at this point, expecting a # flush-pkt from the server. We might be ready to send a packfile # at this point, so we need to explicitly short-circuit in this # case. return [] return want_revs def unread_proto_line(self, command, value): if isinstance(value, int): value = str(value).encode('ascii') self.proto.unread_pkt_line(command + b' ' + value) def ack(self, have_ref): if len(have_ref) != 40: raise ValueError("invalid sha %r" % have_ref) return self._impl.ack(have_ref) def reset(self): self._cached = True self._cache_index = 0 def next(self): if not self._cached: if not self._impl and self.http_req: return None return next(self._impl) self._cache_index += 1 if self._cache_index > len(self._cache): return None return self._cache[self._cache_index] __next__ = next def read_proto_line(self, allowed): """Read a line from the wire. Args: allowed: An iterable of command names that should be allowed. Returns: A tuple of (command, value); see _split_proto_line. Raises: UnexpectedCommandError: If an error occurred reading the line. """ return _split_proto_line(self.proto.read_pkt_line(), allowed) def _handle_shallow_request(self, wants): while True: command, val = self.read_proto_line( (COMMAND_DEEPEN, COMMAND_SHALLOW)) if command == COMMAND_DEEPEN: depth = val break self.client_shallow.add(val) self.read_proto_line((None,)) # consume client's flush-pkt shallow, not_shallow = _find_shallow(self.store, wants, depth) # Update self.shallow instead of reassigning it since we passed a # reference to it before this method was called. self.shallow.update(shallow - not_shallow) new_shallow = self.shallow - self.client_shallow unshallow = self.unshallow = not_shallow & self.client_shallow for sha in sorted(new_shallow): self.proto.write_pkt_line(COMMAND_SHALLOW + b' ' + sha) for sha in sorted(unshallow): self.proto.write_pkt_line(COMMAND_UNSHALLOW + b' ' + sha) self.proto.write_pkt_line(None) def notify_done(self): # relay the message down to the handler. self.handler.notify_done() def send_ack(self, sha, ack_type=b''): if ack_type: ack_type = b' ' + ack_type self.proto.write_pkt_line(b'ACK ' + sha + ack_type + b'\n') def send_nak(self): self.proto.write_pkt_line(b'NAK\n') def handle_done(self, done_required, done_received): # Delegate this to the implementation. return self._impl.handle_done(done_required, done_received) def set_wants(self, wants): self._wants = wants def all_wants_satisfied(self, haves): """Check whether all the current wants are satisfied by a set of haves. Args: haves: A set of commits we know the client has. Note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ return _all_wants_satisfied(self.store, haves, self._wants) def set_ack_type(self, ack_type): impl_classes = { MULTI_ACK: MultiAckGraphWalkerImpl, MULTI_ACK_DETAILED: MultiAckDetailedGraphWalkerImpl, SINGLE_ACK: SingleAckGraphWalkerImpl, } self._impl = impl_classes[ack_type](self) _GRAPH_WALKER_COMMANDS = (COMMAND_HAVE, COMMAND_DONE, None) class SingleAckGraphWalkerImpl(object): """Graph walker implementation that speaks the single-ack protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): if not self._common: self.walker.send_ack(have_ref) self._common.append(have_ref) def next(self): command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command in (None, COMMAND_DONE): # defer the handling of done self.walker.notify_done() return None elif command == COMMAND_HAVE: return sha __next__ = next def handle_done(self, done_required, done_received): if not self._common: self.walker.send_nak() if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False return True class MultiAckGraphWalkerImpl(object): """Graph walker implementation that speaks the multi-ack protocol.""" def __init__(self, walker): self.walker = walker self._found_base = False self._common = [] def ack(self, have_ref): self._common.append(have_ref) if not self._found_base: self.walker.send_ack(have_ref, b'continue') if self.walker.all_wants_satisfied(self._common): self._found_base = True # else we blind ack within next def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: self.walker.send_nak() # in multi-ack mode, a flush-pkt indicates the client wants to # flush but more have lines are still coming continue elif command == COMMAND_DONE: self.walker.notify_done() return None elif command == COMMAND_HAVE: if self._found_base: # blind ack self.walker.send_ack(sha, b'continue') return sha __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class MultiAckDetailedGraphWalkerImpl(object): """Graph walker implementation speaking the multi-ack-detailed protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): # Should only be called iff have_ref is common self._common.append(have_ref) self.walker.send_ack(have_ref, b'common') def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: if self.walker.all_wants_satisfied(self._common): self.walker.send_ack(self._common[-1], b'ready') self.walker.send_nak() if self.walker.http_req: # The HTTP version of this request a flush-pkt always # signifies an end of request, so we also return # nothing here as if we are done (but not really, as # it depends on whether no-done capability was # specified and that's handled in handle_done which # may or may not call post_nodone_check depending on # that). return None elif command == COMMAND_DONE: # Let the walker know that we got a done. self.walker.notify_done() break elif command == COMMAND_HAVE: # return the sha and let the caller ACK it with the # above ack method. return sha # don't nak unless no common commits were found, even if not # everything is satisfied __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class ReceivePackHandler(PackHandler): """Protocol handler for downloading a pack from the client.""" def __init__(self, backend, args, proto, http_req=None, advertise_refs=False): super(ReceivePackHandler, self).__init__( backend, proto, http_req=http_req) self.repo = backend.open_repository(args[0]) self.advertise_refs = advertise_refs @classmethod def capabilities(cls): return [CAPABILITY_REPORT_STATUS, CAPABILITY_DELETE_REFS, CAPABILITY_QUIET, CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K, CAPABILITY_NO_DONE] def _apply_pack(self, refs): all_exceptions = (IOError, OSError, ChecksumMismatch, ApplyDeltaError, AssertionError, socket.error, zlib.error, ObjectFormatException) status = [] will_send_pack = False for command in refs: if command[1] != ZERO_SHA: will_send_pack = True if will_send_pack: # TODO: more informative error messages than just the exception # string try: recv = getattr(self.proto, "recv", None) self.repo.object_store.add_thin_pack(self.proto.read, recv) status.append((b'unpack', b'ok')) except all_exceptions as e: status.append((b'unpack', str(e).replace('\n', ''))) # The pack may still have been moved in, but it may contain # broken objects. We trust a later GC to clean it up. else: # The git protocol want to find a status entry related to unpack # process even if no pack data has been sent. status.append((b'unpack', b'ok')) for oldsha, sha, ref in refs: ref_status = b'ok' try: if sha == ZERO_SHA: if CAPABILITY_DELETE_REFS not in self.capabilities(): raise GitProtocolError( 'Attempted to delete refs without delete-refs ' 'capability.') try: self.repo.refs.remove_if_equals(ref, oldsha) except all_exceptions: ref_status = b'failed to delete' else: try: self.repo.refs.set_if_equals(ref, oldsha, sha) except all_exceptions: ref_status = b'failed to write' except KeyError: ref_status = b'bad ref' status.append((ref, ref_status)) return status def _report_status(self, status): if self.has_capability(CAPABILITY_SIDE_BAND_64K): writer = BufferedPktLineWriter( lambda d: self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, d)) write = writer.write def flush(): writer.flush() self.proto.write_pkt_line(None) else: write = self.proto.write_pkt_line def flush(): pass for name, msg in status: if name == b'unpack': write(b'unpack ' + msg + b'\n') elif msg == b'ok': write(b'ok ' + name + b'\n') else: write(b'ng ' + name + b' ' + msg + b'\n') write(None) flush() def _on_post_receive(self, client_refs): hook = self.repo.hooks.get('post-receive', None) if not hook: return try: output = hook.execute(client_refs) if output: self.proto.write_sideband(SIDE_BAND_CHANNEL_PROGRESS, output) except HookError as err: self.proto.write_sideband(SIDE_BAND_CHANNEL_FATAL, repr(err)) def handle(self): if self.advertise_refs or not self.http_req: refs = sorted(self.repo.get_refs().items()) symrefs = sorted(self.repo.refs.get_symrefs().items()) if not refs: refs = [(CAPABILITIES_REF, ZERO_SHA)] self.proto.write_pkt_line( refs[0][1] + b' ' + refs[0][0] + b'\0' + self.capability_line( self.capabilities() + symref_capabilities(symrefs)) + b'\n') for i in range(1, len(refs)): ref = refs[i] self.proto.write_pkt_line(ref[1] + b' ' + ref[0] + b'\n') self.proto.write_pkt_line(None) if self.advertise_refs: return client_refs = [] ref = self.proto.read_pkt_line() # if ref is none then client doesnt want to send us anything.. if ref is None: return ref, caps = extract_capabilities(ref) self.set_client_capabilities(caps) # client will now send us a list of (oldsha, newsha, ref) while ref: client_refs.append(ref.split()) ref = self.proto.read_pkt_line() # backend can now deal with this refs and read a pack using self.read status = self._apply_pack(client_refs) self._on_post_receive(client_refs) # when we have read all the pack from the client, send a status report # if the client asked for it if self.has_capability(CAPABILITY_REPORT_STATUS): self._report_status(status) class UploadArchiveHandler(Handler): def __init__(self, backend, args, proto, http_req=None): super(UploadArchiveHandler, self).__init__(backend, proto, http_req) self.repo = backend.open_repository(args[0]) def handle(self): def write(x): return self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, x) arguments = [] for pkt in self.proto.read_pkt_seq(): (key, value) = pkt.split(b' ', 1) if key != b'argument': raise GitProtocolError('unknown command %s' % key) arguments.append(value.rstrip(b'\n')) prefix = b'' format = 'tar' i = 0 store = self.repo.object_store while i < len(arguments): argument = arguments[i] if argument == b'--prefix': i += 1 prefix = arguments[i] elif argument == b'--format': i += 1 format = arguments[i].decode('ascii') else: commit_sha = self.repo.refs[argument] tree = store[store[commit_sha].tree] i += 1 self.proto.write_pkt_line(b'ACK\n') self.proto.write_pkt_line(None) for chunk in tar_stream( store, tree, mtime=time.time(), prefix=prefix, format=format): write(chunk) self.proto.write_pkt_line(None) # Default handler classes for git services. DEFAULT_HANDLERS = { b'git-upload-pack': UploadPackHandler, b'git-receive-pack': ReceivePackHandler, b'git-upload-archive': UploadArchiveHandler, } class TCPGitRequestHandler(socketserver.StreamRequestHandler): def __init__(self, handlers, *args, **kwargs): self.handlers = handlers socketserver.StreamRequestHandler.__init__(self, *args, **kwargs) def handle(self): proto = ReceivableProtocol(self.connection.recv, self.wfile.write) command, args = proto.read_cmd() logger.info('Handling %s request, args=%s', command, args) cls = self.handlers.get(command, None) if not callable(cls): raise GitProtocolError('Invalid service %s' % command) h = cls(self.server.backend, args, proto) h.handle() class TCPGitServer(socketserver.TCPServer): allow_reuse_address = True serve = socketserver.TCPServer.serve_forever def _make_handler(self, *args, **kwargs): return TCPGitRequestHandler(self.handlers, *args, **kwargs) def __init__(self, backend, listen_addr, port=TCP_GIT_PORT, handlers=None): self.handlers = dict(DEFAULT_HANDLERS) if handlers is not None: self.handlers.update(handlers) self.backend = backend logger.info('Listening for TCP connections on %s:%d', listen_addr, port) socketserver.TCPServer.__init__(self, (listen_addr, port), self._make_handler) def verify_request(self, request, client_address): logger.info('Handling request from %s', client_address) return True def handle_error(self, request, client_address): logger.exception('Exception happened during processing of request ' 'from %s', client_address) def main(argv=sys.argv): """Entry point for starting a TCP git server.""" import optparse parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="localhost", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") options, args = parser.parse_args(argv) log_utils.default_logging_config() if len(args) > 1: gitdir = args[1] else: gitdir = '.' # TODO(jelmer): Support git-daemon-export-ok and --export-all. backend = FileSystemBackend(gitdir) server = TCPGitServer(backend, options.listen_address, options.port) server.serve_forever() def serve_command(handler_cls, argv=sys.argv, backend=None, inf=sys.stdin, outf=sys.stdout): """Serve a single command. This is mostly useful for the implementation of commands used by e.g. git+ssh. Args: handler_cls: `Handler` class to use for the request argv: execv-style command-line arguments. Defaults to sys.argv. backend: `Backend` to use inf: File-like object to read from, defaults to standard input. outf: File-like object to write to, defaults to standard output. Returns: Exit code for use with sys.exit. 0 on success, 1 on failure. """ if backend is None: backend = FileSystemBackend() def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = handler_cls(backend, argv[1:], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def generate_info_refs(repo): """Generate an info refs file.""" refs = repo.get_refs() return write_info_refs(refs, repo.object_store) def generate_objects_info_packs(repo): """Generate an index for for packs.""" for pack in repo.object_store.packs: yield ( - b'P ' + pack.data.filename.encode(sys.getfilesystemencoding()) + + b'P ' + os.fsencode(pack.data.filename) + b'\n') def update_server_info(repo): """Generate server info for dumb file access. This generates info/refs and objects/info/packs, similar to "git update-server-info". """ repo._put_named_file( os.path.join('info', 'refs'), b"".join(generate_info_refs(repo))) repo._put_named_file( os.path.join('objects', 'info', 'packs'), b"".join(generate_objects_info_packs(repo))) if __name__ == '__main__': main() diff --git a/dulwich/tests/test_index.py b/dulwich/tests/test_index.py index 34bb8ccf..7f632e4a 100644 --- a/dulwich/tests/test_index.py +++ b/dulwich/tests/test_index.py @@ -1,762 +1,762 @@ # -*- coding: utf-8 -*- # test_index.py -- Tests for the git index # encoding: utf-8 # Copyright (C) 2008-2009 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for the index.""" from io import BytesIO import os import shutil import stat import struct import sys import tempfile import warnings from dulwich.index import ( Index, build_index_from_tree, cleanup_mode, commit_tree, get_unstaged_changes, index_entry_from_stat, read_index, read_index_dict, validate_path_element_default, validate_path_element_ntfs, write_cache_time, write_index, write_index_dict, _tree_to_fs_path, _fs_to_tree_path, ) from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.objects import ( Blob, Commit, Tree, S_IFGITLINK, ) from dulwich.repo import Repo from dulwich.tests import ( TestCase, skipIf, ) from dulwich.tests.utils import ( setup_warning_catcher, ) def can_symlink(): """Return whether running process can create symlinks.""" if sys.platform != 'win32': # Platforms other than Windows should allow symlinks without issues. return True if not hasattr(os, 'symlink'): # Older Python versions do not have `os.symlink` on Windows. return False test_source = tempfile.mkdtemp() test_target = test_source + 'can_symlink' try: os.symlink(test_source, test_target) except OSError: return False return True class IndexTestCase(TestCase): datadir = os.path.join(os.path.dirname(__file__), 'data/indexes') def get_simple_index(self, name): return Index(os.path.join(self.datadir, name)) class SimpleIndexTestCase(IndexTestCase): def test_len(self): self.assertEqual(1, len(self.get_simple_index("index"))) def test_iter(self): self.assertEqual([b'bla'], list(self.get_simple_index("index"))) def test_iterobjects(self): self.assertEqual( [(b'bla', b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 33188)], list(self.get_simple_index("index").iterobjects())) def test_iterblobs(self): warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) self.assertEqual( [(b'bla', b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 33188)], list(self.get_simple_index("index").iterblobs())) expected_warning = PendingDeprecationWarning( 'Use iterobjects() instead.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) def test_getitem(self): self.assertEqual( ((1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 0), self.get_simple_index("index")[b"bla"]) def test_empty(self): i = self.get_simple_index("notanindex") self.assertEqual(0, len(i)) self.assertFalse(os.path.exists(i._filename)) def test_against_empty_tree(self): i = self.get_simple_index("index") changes = list(i.changes_from_tree(MemoryObjectStore(), None)) self.assertEqual(1, len(changes)) (oldname, newname), (oldmode, newmode), (oldsha, newsha) = changes[0] self.assertEqual(b'bla', newname) self.assertEqual(b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', newsha) class SimpleIndexWriterTestCase(IndexTestCase): def setUp(self): IndexTestCase.setUp(self) self.tempdir = tempfile.mkdtemp() def tearDown(self): IndexTestCase.tearDown(self) shutil.rmtree(self.tempdir) def test_simple_write(self): entries = [(b'barbla', (1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 0)] filename = os.path.join(self.tempdir, 'test-simple-write-index') with open(filename, 'wb+') as x: write_index(x, entries) with open(filename, 'rb') as x: self.assertEqual(entries, list(read_index(x))) class ReadIndexDictTests(IndexTestCase): def setUp(self): IndexTestCase.setUp(self) self.tempdir = tempfile.mkdtemp() def tearDown(self): IndexTestCase.tearDown(self) shutil.rmtree(self.tempdir) def test_simple_write(self): entries = { b'barbla': ((1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 0)} filename = os.path.join(self.tempdir, 'test-simple-write-index') with open(filename, 'wb+') as x: write_index_dict(x, entries) with open(filename, 'rb') as x: self.assertEqual(entries, read_index_dict(x)) class CommitTreeTests(TestCase): def setUp(self): super(CommitTreeTests, self).setUp() self.store = MemoryObjectStore() def test_single_blob(self): blob = Blob() blob.data = b"foo" self.store.add_object(blob) blobs = [(b"bla", blob.id, stat.S_IFREG)] rootid = commit_tree(self.store, blobs) self.assertEqual(rootid, b"1a1e80437220f9312e855c37ac4398b68e5c1d50") self.assertEqual((stat.S_IFREG, blob.id), self.store[rootid][b"bla"]) self.assertEqual(set([rootid, blob.id]), set(self.store._data.keys())) def test_nested(self): blob = Blob() blob.data = b"foo" self.store.add_object(blob) blobs = [(b"bla/bar", blob.id, stat.S_IFREG)] rootid = commit_tree(self.store, blobs) self.assertEqual(rootid, b"d92b959b216ad0d044671981196781b3258fa537") dirid = self.store[rootid][b"bla"][1] self.assertEqual(dirid, b"c1a1deb9788150829579a8b4efa6311e7b638650") self.assertEqual((stat.S_IFDIR, dirid), self.store[rootid][b"bla"]) self.assertEqual((stat.S_IFREG, blob.id), self.store[dirid][b"bar"]) self.assertEqual(set([rootid, dirid, blob.id]), set(self.store._data.keys())) class CleanupModeTests(TestCase): def assertModeEqual(self, expected, got): self.assertEqual(expected, got, '%o != %o' % (expected, got)) def test_file(self): self.assertModeEqual(0o100644, cleanup_mode(0o100000)) def test_executable(self): self.assertModeEqual(0o100755, cleanup_mode(0o100711)) self.assertModeEqual(0o100755, cleanup_mode(0o100700)) def test_symlink(self): self.assertModeEqual(0o120000, cleanup_mode(0o120711)) def test_dir(self): self.assertModeEqual(0o040000, cleanup_mode(0o40531)) def test_submodule(self): self.assertModeEqual(0o160000, cleanup_mode(0o160744)) class WriteCacheTimeTests(TestCase): def test_write_string(self): f = BytesIO() self.assertRaises(TypeError, write_cache_time, f, "foo") def test_write_int(self): f = BytesIO() write_cache_time(f, 434343) self.assertEqual(struct.pack(">LL", 434343, 0), f.getvalue()) def test_write_tuple(self): f = BytesIO() write_cache_time(f, (434343, 21)) self.assertEqual(struct.pack(">LL", 434343, 21), f.getvalue()) def test_write_float(self): f = BytesIO() write_cache_time(f, 434343.000000021) self.assertEqual(struct.pack(">LL", 434343, 21), f.getvalue()) class IndexEntryFromStatTests(TestCase): def test_simple(self): st = os.stat_result( (16877, 131078, 64769, 154, 1000, 1000, 12288, 1323629595, 1324180496, 1324180496)) entry = index_entry_from_stat(st, "22" * 20, 0) self.assertEqual(entry, ( 1324180496, 1324180496, 64769, 131078, 16384, 1000, 1000, 12288, '2222222222222222222222222222222222222222', 0)) def test_override_mode(self): st = os.stat_result( (stat.S_IFREG + 0o644, 131078, 64769, 154, 1000, 1000, 12288, 1323629595, 1324180496, 1324180496)) entry = index_entry_from_stat( st, "22" * 20, 0, mode=stat.S_IFREG + 0o755) self.assertEqual(entry, ( 1324180496, 1324180496, 64769, 131078, 33261, 1000, 1000, 12288, '2222222222222222222222222222222222222222', 0)) class BuildIndexTests(TestCase): def assertReasonableIndexEntry(self, index_entry, mode, filesize, sha): self.assertEqual(index_entry[4], mode) # mode self.assertEqual(index_entry[7], filesize) # filesize self.assertEqual(index_entry[8], sha) # sha def assertFileContents(self, path, contents, symlink=False): if symlink: self.assertEqual(os.readlink(path), contents) else: with open(path, 'rb') as f: self.assertEqual(f.read(), contents) def test_empty(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: tree = Tree() repo.object_store.add_object(tree) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 0) # Verify no files self.assertEqual(['.git'], os.listdir(repo.path)) def test_git_dir(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b'file a') filee = Blob.from_string(b'd') tree = Tree() tree[b'.git/a'] = (stat.S_IFREG | 0o644, filea.id) tree[b'c/e'] = (stat.S_IFREG | 0o644, filee.id) repo.object_store.add_objects( [(o, None) for o in [filea, filee, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, '.git', 'a') self.assertFalse(os.path.exists(apath)) # filee epath = os.path.join(repo.path, 'c', 'e') self.assertTrue(os.path.exists(epath)) self.assertReasonableIndexEntry( index[b'c/e'], stat.S_IFREG | 0o644, 1, filee.id) self.assertFileContents(epath, b'd') def test_nonempty(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b'file a') fileb = Blob.from_string(b'file b') filed = Blob.from_string(b'file d') tree = Tree() tree[b'a'] = (stat.S_IFREG | 0o644, filea.id) tree[b'b'] = (stat.S_IFREG | 0o644, fileb.id) tree[b'c/d'] = (stat.S_IFREG | 0o644, filed.id) repo.object_store.add_objects( [(o, None) for o in [filea, fileb, filed, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 3) # filea apath = os.path.join(repo.path, 'a') self.assertTrue(os.path.exists(apath)) self.assertReasonableIndexEntry( index[b'a'], stat.S_IFREG | 0o644, 6, filea.id) self.assertFileContents(apath, b'file a') # fileb bpath = os.path.join(repo.path, 'b') self.assertTrue(os.path.exists(bpath)) self.assertReasonableIndexEntry( index[b'b'], stat.S_IFREG | 0o644, 6, fileb.id) self.assertFileContents(bpath, b'file b') # filed dpath = os.path.join(repo.path, 'c', 'd') self.assertTrue(os.path.exists(dpath)) self.assertReasonableIndexEntry( index[b'c/d'], stat.S_IFREG | 0o644, 6, filed.id) self.assertFileContents(dpath, b'file d') # Verify no extra files self.assertEqual( ['.git', 'a', 'b', 'c'], sorted(os.listdir(repo.path))) self.assertEqual( ['d'], sorted(os.listdir(os.path.join(repo.path, 'c')))) @skipIf(not getattr(os, 'sync', None), 'Requires sync support') def test_norewrite(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b'file a') filea_path = os.path.join(repo_dir, 'a') tree = Tree() tree[b'a'] = (stat.S_IFREG | 0o644, filea.id) repo.object_store.add_objects([(o, None) for o in [filea, tree]]) # First Write build_index_from_tree(repo.path, repo.index_path(), repo.object_store, tree.id) # Use sync as metadata can be cached on some FS os.sync() mtime = os.stat(filea_path).st_mtime # Test Rewrite build_index_from_tree(repo.path, repo.index_path(), repo.object_store, tree.id) os.sync() self.assertEqual(mtime, os.stat(filea_path).st_mtime) # Modify content with open(filea_path, 'wb') as fh: fh.write(b'test a') os.sync() mtime = os.stat(filea_path).st_mtime # Test rewrite build_index_from_tree(repo.path, repo.index_path(), repo.object_store, tree.id) os.sync() with open(filea_path, 'rb') as fh: self.assertEqual(b'file a', fh.read()) @skipIf(not can_symlink(), 'Requires symlink support') def test_symlink(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filed = Blob.from_string(b'file d') filee = Blob.from_string(b'd') tree = Tree() tree[b'c/d'] = (stat.S_IFREG | 0o644, filed.id) tree[b'c/e'] = (stat.S_IFLNK, filee.id) # symlink repo.object_store.add_objects( [(o, None) for o in [filed, filee, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() # symlink to d epath = os.path.join(repo.path, 'c', 'e') self.assertTrue(os.path.exists(epath)) self.assertReasonableIndexEntry( index[b'c/e'], stat.S_IFLNK, 0 if sys.platform == 'win32' else 1, filee.id) self.assertFileContents(epath, 'd', symlink=True) def test_no_decode_encode(self): repo_dir = tempfile.mkdtemp() - repo_dir_bytes = repo_dir.encode(sys.getfilesystemencoding()) + repo_dir_bytes = os.fsencode(repo_dir) self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo file = Blob.from_string(b'foo') tree = Tree() latin1_name = u'À'.encode('latin1') latin1_path = os.path.join(repo_dir_bytes, latin1_name) utf8_name = u'À'.encode('utf8') utf8_path = os.path.join(repo_dir_bytes, utf8_name) tree[latin1_name] = (stat.S_IFREG | 0o644, file.id) tree[utf8_name] = (stat.S_IFREG | 0o644, file.id) repo.object_store.add_objects( [(o, None) for o in [file, tree]]) try: os.path.exists(latin1_path) except UnicodeDecodeError: # This happens e.g. with python3.6 on Windows. # It implicitly decodes using utf8, which doesn't work. self.skipTest('can not implicitly convert as utf8') build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertIn(latin1_name, index) self.assertIn(utf8_name, index) self.assertTrue(os.path.exists(latin1_path)) self.assertTrue(os.path.exists(utf8_path)) def test_git_submodule(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: filea = Blob.from_string(b'file alalala') subtree = Tree() subtree[b'a'] = (stat.S_IFREG | 0o644, filea.id) c = Commit() c.tree = subtree.id c.committer = c.author = b'Somebody ' c.commit_time = c.author_time = 42342 c.commit_timezone = c.author_timezone = 0 c.parents = [] c.message = b'Subcommit' tree = Tree() tree[b'c'] = (S_IFGITLINK, c.id) repo.object_store.add_objects( [(o, None) for o in [tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, 'c/a') self.assertFalse(os.path.exists(apath)) # dir c cpath = os.path.join(repo.path, 'c') self.assertTrue(os.path.isdir(cpath)) self.assertEqual(index[b'c'][4], S_IFGITLINK) # mode self.assertEqual(index[b'c'][8], c.id) # sha def test_git_submodule_exists(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: filea = Blob.from_string(b'file alalala') subtree = Tree() subtree[b'a'] = (stat.S_IFREG | 0o644, filea.id) c = Commit() c.tree = subtree.id c.committer = c.author = b'Somebody ' c.commit_time = c.author_time = 42342 c.commit_timezone = c.author_timezone = 0 c.parents = [] c.message = b'Subcommit' tree = Tree() tree[b'c'] = (S_IFGITLINK, c.id) os.mkdir(os.path.join(repo_dir, 'c')) repo.object_store.add_objects( [(o, None) for o in [tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, 'c/a') self.assertFalse(os.path.exists(apath)) # dir c cpath = os.path.join(repo.path, 'c') self.assertTrue(os.path.isdir(cpath)) self.assertEqual(index[b'c'][4], S_IFGITLINK) # mode self.assertEqual(index[b'c'][8], c.id) # sha class GetUnstagedChangesTests(TestCase): def test_get_unstaged_changes(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then modify it foo1_fullpath = os.path.join(repo_dir, 'foo1') with open(foo1_fullpath, 'wb') as f: f.write(b'origstuff') foo2_fullpath = os.path.join(repo_dir, 'foo2') with open(foo2_fullpath, 'wb') as f: f.write(b'origstuff') repo.stage(['foo1', 'foo2']) repo.do_commit(b'test status', author=b'author ', committer=b'committer ') with open(foo1_fullpath, 'wb') as f: f.write(b'newstuff') # modify access and modify time of path os.utime(foo1_fullpath, (0, 0)) changes = get_unstaged_changes(repo.open_index(), repo_dir) self.assertEqual(list(changes), [b'foo1']) def test_get_unstaged_deleted_changes(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then remove it foo1_fullpath = os.path.join(repo_dir, 'foo1') with open(foo1_fullpath, 'wb') as f: f.write(b'origstuff') repo.stage(['foo1']) repo.do_commit(b'test status', author=b'author ', committer=b'committer ') os.unlink(foo1_fullpath) changes = get_unstaged_changes(repo.open_index(), repo_dir) self.assertEqual(list(changes), [b'foo1']) def test_get_unstaged_changes_removed_replaced_by_directory(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then modify it foo1_fullpath = os.path.join(repo_dir, 'foo1') with open(foo1_fullpath, 'wb') as f: f.write(b'origstuff') repo.stage(['foo1']) repo.do_commit(b'test status', author=b'author ', committer=b'committer ') os.remove(foo1_fullpath) os.mkdir(foo1_fullpath) changes = get_unstaged_changes(repo.open_index(), repo_dir) self.assertEqual(list(changes), [b'foo1']) @skipIf(not can_symlink(), 'Requires symlink support') def test_get_unstaged_changes_removed_replaced_by_link(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then modify it foo1_fullpath = os.path.join(repo_dir, 'foo1') with open(foo1_fullpath, 'wb') as f: f.write(b'origstuff') repo.stage(['foo1']) repo.do_commit(b'test status', author=b'author ', committer=b'committer ') os.remove(foo1_fullpath) os.symlink(os.path.dirname(foo1_fullpath), foo1_fullpath) changes = get_unstaged_changes(repo.open_index(), repo_dir) self.assertEqual(list(changes), [b'foo1']) class TestValidatePathElement(TestCase): def test_default(self): self.assertTrue(validate_path_element_default(b"bla")) self.assertTrue(validate_path_element_default(b".bla")) self.assertFalse(validate_path_element_default(b".git")) self.assertFalse(validate_path_element_default(b".giT")) self.assertFalse(validate_path_element_default(b"..")) self.assertTrue(validate_path_element_default(b"git~1")) def test_ntfs(self): self.assertTrue(validate_path_element_ntfs(b"bla")) self.assertTrue(validate_path_element_ntfs(b".bla")) self.assertFalse(validate_path_element_ntfs(b".git")) self.assertFalse(validate_path_element_ntfs(b".giT")) self.assertFalse(validate_path_element_ntfs(b"..")) self.assertFalse(validate_path_element_ntfs(b"git~1")) class TestTreeFSPathConversion(TestCase): def test_tree_to_fs_path(self): tree_path = u'délwíçh/foo'.encode('utf8') fs_path = _tree_to_fs_path(b'/prefix/path', tree_path) self.assertEqual( fs_path, os.path.join(u'/prefix/path', u'délwíçh', u'foo').encode('utf8')) def test_fs_to_tree_path_str(self): fs_path = os.path.join(os.path.join(u'délwíçh', u'foo')) tree_path = _fs_to_tree_path(fs_path, "utf-8") self.assertEqual(tree_path, u'délwíçh/foo'.encode("utf-8")) def test_fs_to_tree_path_bytes(self): fs_path = os.path.join(os.path.join(u'délwíçh', u'foo').encode('utf8')) tree_path = _fs_to_tree_path(fs_path, "utf-8") self.assertEqual(tree_path, u'délwíçh/foo'.encode('utf8')) diff --git a/dulwich/tests/test_refs.py b/dulwich/tests/test_refs.py index b9c76457..2c13a6b0 100644 --- a/dulwich/tests/test_refs.py +++ b/dulwich/tests/test_refs.py @@ -1,693 +1,689 @@ # test_refs.py -- tests for refs.py # encoding: utf-8 # 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. # """Tests for dulwich.refs.""" from io import BytesIO import os import sys import tempfile from dulwich import errors from dulwich.file import ( GitFile, ) from dulwich.objects import ZERO_SHA from dulwich.refs import ( DictRefsContainer, InfoRefsContainer, check_ref_format, _split_ref_line, parse_symref_value, read_packed_refs_with_peeled, read_packed_refs, strip_peeled_refs, write_packed_refs, ) from dulwich.repo import Repo from dulwich.tests import ( SkipTest, TestCase, ) from dulwich.tests.utils import ( open_repo, tear_down_repo, ) class CheckRefFormatTests(TestCase): """Tests for the check_ref_format function. These are the same tests as in the git test suite. """ def test_valid(self): self.assertTrue(check_ref_format(b'heads/foo')) self.assertTrue(check_ref_format(b'foo/bar/baz')) self.assertTrue(check_ref_format(b'refs///heads/foo')) self.assertTrue(check_ref_format(b'foo./bar')) self.assertTrue(check_ref_format(b'heads/foo@bar')) self.assertTrue(check_ref_format(b'heads/fix.lock.error')) def test_invalid(self): self.assertFalse(check_ref_format(b'foo')) self.assertFalse(check_ref_format(b'heads/foo/')) self.assertFalse(check_ref_format(b'./foo')) self.assertFalse(check_ref_format(b'.refs/foo')) self.assertFalse(check_ref_format(b'heads/foo..bar')) self.assertFalse(check_ref_format(b'heads/foo?bar')) self.assertFalse(check_ref_format(b'heads/foo.lock')) self.assertFalse(check_ref_format(b'heads/v@{ation')) self.assertFalse(check_ref_format(b'heads/foo\bar')) ONES = b'1' * 40 TWOS = b'2' * 40 THREES = b'3' * 40 FOURS = b'4' * 40 class PackedRefsFileTests(TestCase): def test_split_ref_line_errors(self): self.assertRaises(errors.PackedRefsException, _split_ref_line, b'singlefield') self.assertRaises(errors.PackedRefsException, _split_ref_line, b'badsha name') self.assertRaises(errors.PackedRefsException, _split_ref_line, ONES + b' bad/../refname') def test_read_without_peeled(self): f = BytesIO(b'\n'.join([ b'# comment', ONES + b' ref/1', TWOS + b' ref/2'])) self.assertEqual([(ONES, b'ref/1'), (TWOS, b'ref/2')], list(read_packed_refs(f))) def test_read_without_peeled_errors(self): f = BytesIO(b'\n'.join([ ONES + b' ref/1', b'^' + TWOS])) self.assertRaises(errors.PackedRefsException, list, read_packed_refs(f)) def test_read_with_peeled(self): f = BytesIO(b'\n'.join([ ONES + b' ref/1', TWOS + b' ref/2', b'^' + THREES, FOURS + b' ref/4'])) self.assertEqual([ (ONES, b'ref/1', None), (TWOS, b'ref/2', THREES), (FOURS, b'ref/4', None), ], list(read_packed_refs_with_peeled(f))) def test_read_with_peeled_errors(self): f = BytesIO(b'\n'.join([ b'^' + TWOS, ONES + b' ref/1'])) self.assertRaises(errors.PackedRefsException, list, read_packed_refs(f)) f = BytesIO(b'\n'.join([ ONES + b' ref/1', b'^' + TWOS, b'^' + THREES])) self.assertRaises(errors.PackedRefsException, list, read_packed_refs(f)) def test_write_with_peeled(self): f = BytesIO() write_packed_refs(f, {b'ref/1': ONES, b'ref/2': TWOS}, {b'ref/1': THREES}) self.assertEqual( b'\n'.join([b'# pack-refs with: peeled', ONES + b' ref/1', b'^' + THREES, TWOS + b' ref/2']) + b'\n', f.getvalue()) def test_write_without_peeled(self): f = BytesIO() write_packed_refs(f, {b'ref/1': ONES, b'ref/2': TWOS}) self.assertEqual(b'\n'.join([ONES + b' ref/1', TWOS + b' ref/2']) + b'\n', f.getvalue()) # Dict of refs that we expect all RefsContainerTests subclasses to define. _TEST_REFS = { b'HEAD': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/heads/40-char-ref-aaaaaaaaaaaaaaaaaa': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/heads/master': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/heads/packed': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/tags/refs-0.1': b'df6800012397fb85c56e7418dd4eb9405dee075c', b'refs/tags/refs-0.2': b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8', b'refs/heads/loop': b'ref: refs/heads/loop', } class RefsContainerTests(object): def test_keys(self): actual_keys = set(self._refs.keys()) self.assertEqual(set(self._refs.allkeys()), actual_keys) self.assertEqual(set(_TEST_REFS.keys()), actual_keys) actual_keys = self._refs.keys(b'refs/heads') actual_keys.discard(b'loop') self.assertEqual( [b'40-char-ref-aaaaaaaaaaaaaaaaaa', b'master', b'packed'], sorted(actual_keys)) self.assertEqual([b'refs-0.1', b'refs-0.2'], sorted(self._refs.keys(b'refs/tags'))) def test_iter(self): actual_keys = set(self._refs.keys()) self.assertEqual(set(self._refs), actual_keys) self.assertEqual(set(_TEST_REFS.keys()), actual_keys) def test_as_dict(self): # refs/heads/loop does not show up even if it exists expected_refs = dict(_TEST_REFS) del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, self._refs.as_dict()) def test_get_symrefs(self): self._refs.set_symbolic_ref(b'refs/heads/src', b'refs/heads/dst') symrefs = self._refs.get_symrefs() if b'HEAD' in symrefs: symrefs.pop(b'HEAD') self.assertEqual({b'refs/heads/src': b'refs/heads/dst', b'refs/heads/loop': b'refs/heads/loop'}, symrefs) def test_setitem(self): self._refs[b'refs/some/ref'] = ( b'42d06bd4b77fed026b154d16493e5deab78f02ec') self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/some/ref']) self.assertRaises( errors.RefFormatError, self._refs.__setitem__, b'notrefs/foo', b'42d06bd4b77fed026b154d16493e5deab78f02ec') def test_set_if_equals(self): nines = b'9' * 40 self.assertFalse(self._refs.set_if_equals(b'HEAD', b'c0ffee', nines)) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'HEAD']) self.assertTrue(self._refs.set_if_equals( b'HEAD', b'42d06bd4b77fed026b154d16493e5deab78f02ec', nines)) self.assertEqual(nines, self._refs[b'HEAD']) # Setting the ref again is a no-op, but will return True. self.assertTrue(self._refs.set_if_equals(b'HEAD', nines, nines)) self.assertEqual(nines, self._refs[b'HEAD']) self.assertTrue(self._refs.set_if_equals(b'refs/heads/master', None, nines)) self.assertEqual(nines, self._refs[b'refs/heads/master']) self.assertTrue(self._refs.set_if_equals( b'refs/heads/nonexistant', ZERO_SHA, nines)) self.assertEqual(nines, self._refs[b'refs/heads/nonexistant']) def test_add_if_new(self): nines = b'9' * 40 self.assertFalse(self._refs.add_if_new(b'refs/heads/master', nines)) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/master']) self.assertTrue(self._refs.add_if_new(b'refs/some/ref', nines)) self.assertEqual(nines, self._refs[b'refs/some/ref']) def test_set_symbolic_ref(self): self._refs.set_symbolic_ref(b'refs/heads/symbolic', b'refs/heads/master') self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'refs/heads/symbolic')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/symbolic']) def test_set_symbolic_ref_overwrite(self): nines = b'9' * 40 self.assertFalse(b'refs/heads/symbolic' in self._refs) self._refs[b'refs/heads/symbolic'] = nines self.assertEqual(nines, self._refs.read_loose_ref(b'refs/heads/symbolic')) self._refs.set_symbolic_ref(b'refs/heads/symbolic', b'refs/heads/master') self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'refs/heads/symbolic')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/symbolic']) def test_check_refname(self): self._refs._check_refname(b'HEAD') self._refs._check_refname(b'refs/stash') self._refs._check_refname(b'refs/heads/foo') self.assertRaises(errors.RefFormatError, self._refs._check_refname, b'refs') self.assertRaises(errors.RefFormatError, self._refs._check_refname, b'notrefs/foo') def test_contains(self): self.assertTrue(b'refs/heads/master' in self._refs) self.assertFalse(b'refs/heads/bar' in self._refs) def test_delitem(self): self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/master']) del self._refs[b'refs/heads/master'] self.assertRaises(KeyError, lambda: self._refs[b'refs/heads/master']) def test_remove_if_equals(self): self.assertFalse(self._refs.remove_if_equals(b'HEAD', b'c0ffee')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'HEAD']) self.assertTrue(self._refs.remove_if_equals( b'refs/tags/refs-0.2', b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8')) self.assertTrue(self._refs.remove_if_equals( b'refs/tags/refs-0.2', ZERO_SHA)) self.assertFalse(b'refs/tags/refs-0.2' in self._refs) def test_import_refs_name(self): self._refs[b'refs/remotes/origin/other'] = ( b'48d01bd4b77fed026b154d16493e5deab78f02ec') self._refs.import_refs( b'refs/remotes/origin', {b'master': b'42d06bd4b77fed026b154d16493e5deab78f02ec'}) self.assertEqual( b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/remotes/origin/master']) self.assertEqual( b'48d01bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/remotes/origin/other']) def test_import_refs_name_prune(self): self._refs[b'refs/remotes/origin/other'] = ( b'48d01bd4b77fed026b154d16493e5deab78f02ec') self._refs.import_refs( b'refs/remotes/origin', {b'master': b'42d06bd4b77fed026b154d16493e5deab78f02ec'}, prune=True) self.assertEqual( b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/remotes/origin/master']) self.assertNotIn( b'refs/remotes/origin/other', self._refs) class DictRefsContainerTests(RefsContainerTests, TestCase): def setUp(self): TestCase.setUp(self) self._refs = DictRefsContainer(dict(_TEST_REFS)) def test_invalid_refname(self): # FIXME: Move this test into RefsContainerTests, but requires # some way of injecting invalid refs. self._refs._refs[b'refs/stash'] = b'00' * 20 expected_refs = dict(_TEST_REFS) del expected_refs[b'refs/heads/loop'] expected_refs[b'refs/stash'] = b'00' * 20 self.assertEqual(expected_refs, self._refs.as_dict()) class DiskRefsContainerTests(RefsContainerTests, TestCase): def setUp(self): TestCase.setUp(self) self._repo = open_repo('refs.git') self.addCleanup(tear_down_repo, self._repo) self._refs = self._repo.refs def test_get_packed_refs(self): self.assertEqual({ b'refs/heads/packed': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/tags/refs-0.1': b'df6800012397fb85c56e7418dd4eb9405dee075c', }, self._refs.get_packed_refs()) def test_get_peeled_not_packed(self): # not packed self.assertEqual(None, self._refs.get_peeled(b'refs/tags/refs-0.2')) self.assertEqual(b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8', self._refs[b'refs/tags/refs-0.2']) # packed, known not peelable self.assertEqual(self._refs[b'refs/heads/packed'], self._refs.get_peeled(b'refs/heads/packed')) # packed, peeled self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs.get_peeled(b'refs/tags/refs-0.1')) def test_setitem(self): RefsContainerTests.test_setitem(self) path = os.path.join(self._refs.path, b'refs', b'some', b'ref') with open(path, 'rb') as f: self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', f.read()[:40]) self.assertRaises( OSError, self._refs.__setitem__, b'refs/some/ref/sub', b'42d06bd4b77fed026b154d16493e5deab78f02ec') def test_setitem_packed(self): with open(os.path.join(self._refs.path, b'packed-refs'), 'w') as f: f.write('# pack-refs with: peeled fully-peeled sorted \n') f.write( '42d06bd4b77fed026b154d16493e5deab78f02ec refs/heads/packed\n') # It's allowed to set a new ref on a packed ref, the new ref will be # placed outside on refs/ self._refs[b'refs/heads/packed'] = ( b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8' ) packed_ref_path = os.path.join( self._refs.path, b'refs', b'heads', b'packed') with open(packed_ref_path, 'rb') as f: self.assertEqual( b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8', f.read()[:40]) self.assertRaises( OSError, self._refs.__setitem__, b'refs/heads/packed/sub', b'42d06bd4b77fed026b154d16493e5deab78f02ec') def test_setitem_symbolic(self): ones = b'1' * 40 self._refs[b'HEAD'] = ones self.assertEqual(ones, self._refs[b'HEAD']) # ensure HEAD was not modified f = open(os.path.join(self._refs.path, b'HEAD'), 'rb') v = next(iter(f)).rstrip(b'\n\r') f.close() self.assertEqual(b'ref: refs/heads/master', v) # ensure the symbolic link was written through f = open(os.path.join(self._refs.path, b'refs', b'heads', b'master'), 'rb') self.assertEqual(ones, f.read()[:40]) f.close() def test_set_if_equals(self): RefsContainerTests.test_set_if_equals(self) # ensure symref was followed self.assertEqual(b'9' * 40, self._refs[b'refs/heads/master']) # ensure lockfile was deleted self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'refs', b'heads', b'master.lock'))) self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'HEAD.lock'))) def test_add_if_new_packed(self): # don't overwrite packed ref self.assertFalse(self._refs.add_if_new(b'refs/tags/refs-0.1', b'9' * 40)) self.assertEqual(b'df6800012397fb85c56e7418dd4eb9405dee075c', self._refs[b'refs/tags/refs-0.1']) def test_add_if_new_symbolic(self): # Use an empty repo instead of the default. repo_dir = os.path.join(tempfile.mkdtemp(), 'test') os.makedirs(repo_dir) repo = Repo.init(repo_dir) self.addCleanup(tear_down_repo, repo) refs = repo.refs nines = b'9' * 40 self.assertEqual(b'ref: refs/heads/master', refs.read_ref(b'HEAD')) self.assertFalse(b'refs/heads/master' in refs) self.assertTrue(refs.add_if_new(b'HEAD', nines)) self.assertEqual(b'ref: refs/heads/master', refs.read_ref(b'HEAD')) self.assertEqual(nines, refs[b'HEAD']) self.assertEqual(nines, refs[b'refs/heads/master']) self.assertFalse(refs.add_if_new(b'HEAD', b'1' * 40)) self.assertEqual(nines, refs[b'HEAD']) self.assertEqual(nines, refs[b'refs/heads/master']) def test_follow(self): self.assertEqual(([b'HEAD', b'refs/heads/master'], b'42d06bd4b77fed026b154d16493e5deab78f02ec'), self._refs.follow(b'HEAD')) self.assertEqual(([b'refs/heads/master'], b'42d06bd4b77fed026b154d16493e5deab78f02ec'), self._refs.follow(b'refs/heads/master')) self.assertRaises(KeyError, self._refs.follow, b'refs/heads/loop') def test_delitem(self): RefsContainerTests.test_delitem(self) ref_file = os.path.join(self._refs.path, b'refs', b'heads', b'master') self.assertFalse(os.path.exists(ref_file)) self.assertFalse(b'refs/heads/master' in self._refs.get_packed_refs()) def test_delitem_symbolic(self): self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'HEAD')) del self._refs[b'HEAD'] self.assertRaises(KeyError, lambda: self._refs[b'HEAD']) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/master']) self.assertFalse( os.path.exists(os.path.join(self._refs.path, b'HEAD'))) def test_remove_if_equals_symref(self): # HEAD is a symref, so shouldn't equal its dereferenced value self.assertFalse(self._refs.remove_if_equals( b'HEAD', b'42d06bd4b77fed026b154d16493e5deab78f02ec')) self.assertTrue(self._refs.remove_if_equals( b'refs/heads/master', b'42d06bd4b77fed026b154d16493e5deab78f02ec')) self.assertRaises(KeyError, lambda: self._refs[b'refs/heads/master']) # HEAD is now a broken symref self.assertRaises(KeyError, lambda: self._refs[b'HEAD']) self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'HEAD')) self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'refs', b'heads', b'master.lock'))) self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'HEAD.lock'))) def test_remove_packed_without_peeled(self): refs_file = os.path.join(self._repo.path, 'packed-refs') f = GitFile(refs_file) refs_data = f.read() f.close() f = GitFile(refs_file, 'wb') f.write(b'\n'.join(l for l in refs_data.split(b'\n') if not l or l[0] not in b'#^')) f.close() self._repo = Repo(self._repo.path) refs = self._repo.refs self.assertTrue(refs.remove_if_equals( b'refs/heads/packed', b'42d06bd4b77fed026b154d16493e5deab78f02ec')) def test_remove_if_equals_packed(self): # test removing ref that is only packed self.assertEqual(b'df6800012397fb85c56e7418dd4eb9405dee075c', self._refs[b'refs/tags/refs-0.1']) self.assertTrue( self._refs.remove_if_equals( b'refs/tags/refs-0.1', b'df6800012397fb85c56e7418dd4eb9405dee075c')) self.assertRaises(KeyError, lambda: self._refs[b'refs/tags/refs-0.1']) def test_remove_parent(self): self._refs[b'refs/heads/foo/bar'] = ( b'df6800012397fb85c56e7418dd4eb9405dee075c' ) del self._refs[b'refs/heads/foo/bar'] ref_file = os.path.join( self._refs.path, b'refs', b'heads', b'foo', b'bar', ) self.assertFalse(os.path.exists(ref_file)) ref_file = os.path.join(self._refs.path, b'refs', b'heads', b'foo') self.assertFalse(os.path.exists(ref_file)) ref_file = os.path.join(self._refs.path, b'refs', b'heads') self.assertTrue(os.path.exists(ref_file)) self._refs[b'refs/heads/foo'] = ( b'df6800012397fb85c56e7418dd4eb9405dee075c' ) def test_read_ref(self): self.assertEqual(b'ref: refs/heads/master', self._refs.read_ref(b'HEAD')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs.read_ref(b'refs/heads/packed')) self.assertEqual(None, self._refs.read_ref(b'nonexistant')) def test_read_loose_ref(self): self._refs[b'refs/heads/foo'] = ( b'df6800012397fb85c56e7418dd4eb9405dee075c' ) self.assertEqual(None, self._refs.read_ref(b'refs/heads/foo/bar')) def test_non_ascii(self): try: - encoded_ref = u'refs/tags/schön'.encode( - sys.getfilesystemencoding()) + encoded_ref = os.fsencode(u'refs/tags/schön') except UnicodeEncodeError: raise SkipTest( "filesystem encoding doesn't support special character") - p = os.path.join( - self._repo.path.encode(sys.getfilesystemencoding()), - encoded_ref) + p = os.path.join(os.fsencode(self._repo.path), encoded_ref) with open(p, 'w') as f: f.write('00' * 20) expected_refs = dict(_TEST_REFS) expected_refs[encoded_ref] = b'00' * 20 del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, self._repo.get_refs()) def test_cyrillic(self): if sys.platform == 'win32': raise SkipTest( "filesystem encoding doesn't support arbitrary bytes") # reported in https://github.com/dulwich/dulwich/issues/608 name = b'\xcd\xee\xe2\xe0\xff\xe2\xe5\xf2\xea\xe01' encoded_ref = b'refs/heads/' + name with open(os.path.join( - self._repo.path.encode( - sys.getfilesystemencoding()), encoded_ref), 'w') as f: + os.fsencode(self._repo.path), encoded_ref), 'w') as f: f.write('00' * 20) expected_refs = set(_TEST_REFS.keys()) expected_refs.add(encoded_ref) self.assertEqual(expected_refs, set(self._repo.refs.allkeys())) self.assertEqual({r[len(b'refs/'):] for r in expected_refs if r.startswith(b'refs/')}, set(self._repo.refs.subkeys(b'refs/'))) expected_refs.remove(b'refs/heads/loop') expected_refs.add(b'HEAD') self.assertEqual(expected_refs, set(self._repo.get_refs().keys())) _TEST_REFS_SERIALIZED = ( b'42d06bd4b77fed026b154d16493e5deab78f02ec\t' b'refs/heads/40-char-ref-aaaaaaaaaaaaaaaaaa\n' b'42d06bd4b77fed026b154d16493e5deab78f02ec\trefs/heads/master\n' b'42d06bd4b77fed026b154d16493e5deab78f02ec\trefs/heads/packed\n' b'df6800012397fb85c56e7418dd4eb9405dee075c\trefs/tags/refs-0.1\n' b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8\trefs/tags/refs-0.2\n') class InfoRefsContainerTests(TestCase): def test_invalid_refname(self): text = _TEST_REFS_SERIALIZED + b'00' * 20 + b'\trefs/stash\n' refs = InfoRefsContainer(BytesIO(text)) expected_refs = dict(_TEST_REFS) del expected_refs[b'HEAD'] expected_refs[b'refs/stash'] = b'00' * 20 del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, refs.as_dict()) def test_keys(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) actual_keys = set(refs.keys()) self.assertEqual(set(refs.allkeys()), actual_keys) expected_refs = dict(_TEST_REFS) del expected_refs[b'HEAD'] del expected_refs[b'refs/heads/loop'] self.assertEqual(set(expected_refs.keys()), actual_keys) actual_keys = refs.keys(b'refs/heads') actual_keys.discard(b'loop') self.assertEqual( [b'40-char-ref-aaaaaaaaaaaaaaaaaa', b'master', b'packed'], sorted(actual_keys)) self.assertEqual([b'refs-0.1', b'refs-0.2'], sorted(refs.keys(b'refs/tags'))) def test_as_dict(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) # refs/heads/loop does not show up even if it exists expected_refs = dict(_TEST_REFS) del expected_refs[b'HEAD'] del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, refs.as_dict()) def test_contains(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) self.assertTrue(b'refs/heads/master' in refs) self.assertFalse(b'refs/heads/bar' in refs) def test_get_peeled(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) # refs/heads/loop does not show up even if it exists self.assertEqual( _TEST_REFS[b'refs/heads/master'], refs.get_peeled(b'refs/heads/master')) class ParseSymrefValueTests(TestCase): def test_valid(self): self.assertEqual( b'refs/heads/foo', parse_symref_value(b'ref: refs/heads/foo')) def test_invalid(self): self.assertRaises(ValueError, parse_symref_value, b'foobar') class StripPeeledRefsTests(TestCase): all_refs = { b'refs/heads/master': b'8843d7f92416211de9ebb963ff4ce28125932878', b'refs/heads/testing': b'186a005b134d8639a58b6731c7c1ea821a6eedba', b'refs/tags/1.0.0': b'a93db4b0360cc635a2b93675010bac8d101f73f0', b'refs/tags/1.0.0^{}': b'a93db4b0360cc635a2b93675010bac8d101f73f0', b'refs/tags/2.0.0': b'0749936d0956c661ac8f8d3483774509c165f89e', b'refs/tags/2.0.0^{}': b'0749936d0956c661ac8f8d3483774509c165f89e', } non_peeled_refs = { b'refs/heads/master': b'8843d7f92416211de9ebb963ff4ce28125932878', b'refs/heads/testing': b'186a005b134d8639a58b6731c7c1ea821a6eedba', b'refs/tags/1.0.0': b'a93db4b0360cc635a2b93675010bac8d101f73f0', b'refs/tags/2.0.0': b'0749936d0956c661ac8f8d3483774509c165f89e', } def test_strip_peeled_refs(self): # Simple check of two dicts self.assertEqual( strip_peeled_refs(self.all_refs), self.non_peeled_refs) diff --git a/dulwich/tests/test_repository.py b/dulwich/tests/test_repository.py index 37158420..23a78e09 100644 --- a/dulwich/tests/test_repository.py +++ b/dulwich/tests/test_repository.py @@ -1,1149 +1,1148 @@ # -*- coding: utf-8 -*- # test_repository.py -- tests for repository.py # Copyright (C) 2007 James Westby # # 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. # """Tests for the repository.""" import locale import os import stat import shutil import sys import tempfile import warnings from dulwich import errors from dulwich.object_store import ( tree_lookup_path, ) from dulwich import objects from dulwich.config import Config from dulwich.errors import NotGitRepository from dulwich.repo import ( InvalidUserIdentity, Repo, MemoryRepo, check_user_identity, ) from dulwich.tests import ( TestCase, skipIf, ) from dulwich.tests.utils import ( open_repo, tear_down_repo, setup_warning_catcher, ) missing_sha = b'b91fa4d900e17e99b433218e988c4eb4a3e9a097' class CreateRepositoryTests(TestCase): def assertFileContentsEqual(self, expected, repo, path): f = repo.get_named_file(path) if not f: self.assertEqual(expected, None) else: with f: self.assertEqual(expected, f.read()) def _check_repo_contents(self, repo, expect_bare): self.assertEqual(expect_bare, repo.bare) self.assertFileContentsEqual( b'Unnamed repository', repo, 'description') self.assertFileContentsEqual( b'', repo, os.path.join('info', 'exclude')) self.assertFileContentsEqual(None, repo, 'nonexistent file') barestr = b'bare = ' + str(expect_bare).lower().encode('ascii') with repo.get_named_file('config') as f: config_text = f.read() self.assertTrue(barestr in config_text, "%r" % config_text) expect_filemode = sys.platform != 'win32' barestr = b'filemode = ' + str(expect_filemode).lower().encode('ascii') with repo.get_named_file('config') as f: config_text = f.read() self.assertTrue(barestr in config_text, "%r" % config_text) def test_create_memory(self): repo = MemoryRepo.init_bare([], {}) self._check_repo_contents(repo, True) def test_create_disk_bare(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init_bare(tmp_dir) self.assertEqual(tmp_dir, repo._controldir) self._check_repo_contents(repo, True) def test_create_disk_non_bare(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(tmp_dir) self.assertEqual(os.path.join(tmp_dir, '.git'), repo._controldir) self._check_repo_contents(repo, False) def test_create_disk_non_bare_mkdir(self): tmp_dir = tempfile.mkdtemp() target_dir = os.path.join(tmp_dir, "target") self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(target_dir, mkdir=True) self.assertEqual(os.path.join(target_dir, '.git'), repo._controldir) self._check_repo_contents(repo, False) def test_create_disk_bare_mkdir(self): tmp_dir = tempfile.mkdtemp() target_dir = os.path.join(tmp_dir, "target") self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init_bare(target_dir, mkdir=True) self.assertEqual(target_dir, repo._controldir) self._check_repo_contents(repo, True) class MemoryRepoTests(TestCase): def test_set_description(self): r = MemoryRepo.init_bare([], {}) description = b"Some description" r.set_description(description) self.assertEqual(description, r.get_description()) class RepositoryRootTests(TestCase): def mkdtemp(self): return tempfile.mkdtemp() def open_repo(self, name): temp_dir = self.mkdtemp() repo = open_repo(name, temp_dir) self.addCleanup(tear_down_repo, repo) return repo def test_simple_props(self): r = self.open_repo('a.git') self.assertEqual(r.controldir(), r.path) def test_setitem(self): r = self.open_repo('a.git') r[b"refs/tags/foo"] = b'a90fa2d900a17e99b433217e988c4eb4a2e9a097' self.assertEqual(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', r[b"refs/tags/foo"].id) def test_getitem_unicode(self): r = self.open_repo('a.git') test_keys = [ (b'refs/heads/master', True), (b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', True), (b'11' * 19 + b'--', False), ] for k, contained in test_keys: self.assertEqual(k in r, contained) # Avoid deprecation warning under Py3.2+ if getattr(self, 'assertRaisesRegex', None): assertRaisesRegexp = self.assertRaisesRegex else: assertRaisesRegexp = self.assertRaisesRegexp for k, _ in test_keys: assertRaisesRegexp( TypeError, "'name' must be bytestring, not int", r.__getitem__, 12 ) def test_delitem(self): r = self.open_repo('a.git') del r[b'refs/heads/master'] self.assertRaises(KeyError, lambda: r[b'refs/heads/master']) del r[b'HEAD'] self.assertRaises(KeyError, lambda: r[b'HEAD']) self.assertRaises(ValueError, r.__delitem__, b'notrefs/foo') def test_get_refs(self): r = self.open_repo('a.git') self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, r.get_refs()) def test_head(self): r = self.open_repo('a.git') self.assertEqual(r.head(), b'a90fa2d900a17e99b433217e988c4eb4a2e9a097') def test_get_object(self): r = self.open_repo('a.git') obj = r.get_object(r.head()) self.assertEqual(obj.type_name, b'commit') def test_get_object_non_existant(self): r = self.open_repo('a.git') self.assertRaises(KeyError, r.get_object, missing_sha) def test_contains_object(self): r = self.open_repo('a.git') self.assertTrue(r.head() in r) def test_contains_ref(self): r = self.open_repo('a.git') self.assertTrue(b"HEAD" in r) def test_get_no_description(self): r = self.open_repo('a.git') self.assertIs(None, r.get_description()) def test_get_description(self): r = self.open_repo('a.git') with open(os.path.join(r.path, 'description'), 'wb') as f: f.write(b"Some description") self.assertEqual(b"Some description", r.get_description()) def test_set_description(self): r = self.open_repo('a.git') description = b"Some description" r.set_description(description) self.assertEqual(description, r.get_description()) def test_contains_missing(self): r = self.open_repo('a.git') self.assertFalse(b"bar" in r) def test_get_peeled(self): # unpacked ref r = self.open_repo('a.git') tag_sha = b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a' self.assertNotEqual(r[tag_sha].sha().hexdigest(), r.head()) self.assertEqual(r.get_peeled(b'refs/tags/mytag'), r.head()) # packed ref with cached peeled value packed_tag_sha = b'b0931cadc54336e78a1d980420e3268903b57a50' parent_sha = r[r.head()].parents[0] self.assertNotEqual(r[packed_tag_sha].sha().hexdigest(), parent_sha) self.assertEqual(r.get_peeled(b'refs/tags/mytag-packed'), parent_sha) # TODO: add more corner cases to test repo def test_get_peeled_not_tag(self): r = self.open_repo('a.git') self.assertEqual(r.get_peeled(b'HEAD'), r.head()) def test_get_walker(self): r = self.open_repo('a.git') # include defaults to [r.head()] self.assertEqual( [e.commit.id for e in r.get_walker()], [r.head(), b'2a72d929692c41d8554c07f6301757ba18a65d91']) self.assertEqual( [e.commit.id for e in r.get_walker([b'2a72d929692c41d8554c07f6301757ba18a65d91'])], [b'2a72d929692c41d8554c07f6301757ba18a65d91']) self.assertEqual( [e.commit.id for e in r.get_walker(b'2a72d929692c41d8554c07f6301757ba18a65d91')], [b'2a72d929692c41d8554c07f6301757ba18a65d91']) def assertFilesystemHidden(self, path): if sys.platform != 'win32': return import ctypes from ctypes.wintypes import DWORD, LPCWSTR GetFileAttributesW = ctypes.WINFUNCTYPE(DWORD, LPCWSTR)( ('GetFileAttributesW', ctypes.windll.kernel32)) self.assertTrue(2 & GetFileAttributesW(path)) def test_init_existing(self): tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = Repo.init(tmp_dir) self.addCleanup(t.close) self.assertEqual(os.listdir(tmp_dir), ['.git']) self.assertFilesystemHidden(os.path.join(tmp_dir, '.git')) def test_init_mkdir(self): tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo_dir = os.path.join(tmp_dir, 'a-repo') t = Repo.init(repo_dir, mkdir=True) self.addCleanup(t.close) self.assertEqual(os.listdir(repo_dir), ['.git']) self.assertFilesystemHidden(os.path.join(repo_dir, '.git')) def test_init_mkdir_unicode(self): repo_name = u'\xa7' try: - repo_name.encode(sys.getfilesystemencoding()) + os.fsencode(repo_name) except UnicodeEncodeError: self.skipTest('filesystem lacks unicode support') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo_dir = os.path.join(tmp_dir, repo_name) t = Repo.init(repo_dir, mkdir=True) self.addCleanup(t.close) self.assertEqual(os.listdir(repo_dir), ['.git']) self.assertFilesystemHidden(os.path.join(repo_dir, '.git')) @skipIf(sys.platform == 'win32', 'fails on Windows') def test_fetch(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = Repo.init(tmp_dir) self.addCleanup(t.close) r.fetch(t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', t) self.assertIn(b'b0931cadc54336e78a1d980420e3268903b57a50', t) @skipIf(sys.platform == 'win32', 'fails on Windows') def test_fetch_ignores_missing_refs(self): r = self.open_repo('a.git') missing = b'1234566789123456789123567891234657373833' r.refs[b'refs/heads/blah'] = missing tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = Repo.init(tmp_dir) self.addCleanup(t.close) r.fetch(t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', t) self.assertIn(b'b0931cadc54336e78a1d980420e3268903b57a50', t) self.assertNotIn(missing, t) def test_clone(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) with r.clone(tmp_dir, mkdir=False) as t: self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/remotes/origin/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, t.refs.as_dict()) shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [t.head(), b'2a72d929692c41d8554c07f6301757ba18a65d91']) c = t.get_config() encoded_path = r.path if not isinstance(encoded_path, bytes): - encoded_path = encoded_path.encode(sys.getfilesystemencoding()) - self.assertEqual(encoded_path, - c.get((b'remote', b'origin'), b'url')) + encoded_path = os.fsencode(encoded_path) + self.assertEqual(encoded_path, c.get((b'remote', b'origin'), b'url')) self.assertEqual( b'+refs/heads/*:refs/remotes/origin/*', c.get((b'remote', b'origin'), b'fetch')) def test_clone_no_head(self): temp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) repo_dir = os.path.join(os.path.dirname(__file__), 'data', 'repos') dest_dir = os.path.join(temp_dir, 'a.git') shutil.copytree(os.path.join(repo_dir, 'a.git'), dest_dir, symlinks=True) r = Repo(dest_dir) del r.refs[b"refs/heads/master"] del r.refs[b"HEAD"] t = r.clone(os.path.join(temp_dir, 'b.git'), mkdir=True) self.assertEqual({ b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, t.refs.as_dict()) def test_clone_empty(self): """Test clone() doesn't crash if HEAD points to a non-existing ref. This simulates cloning server-side bare repository either when it is still empty or if user renames master branch and pushes private repo to the server. Non-bare repo HEAD always points to an existing ref. """ r = self.open_repo('empty.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) r.clone(tmp_dir, mkdir=False, bare=True) def test_clone_bare(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = r.clone(tmp_dir, mkdir=False) t.close() def test_clone_checkout_and_bare(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) self.assertRaises(ValueError, r.clone, tmp_dir, mkdir=False, checkout=True, bare=True) def test_merge_history(self): r = self.open_repo('simple_merge.git') shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [b'5dac377bdded4c9aeb8dff595f0faeebcc8498cc', b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6', b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310']) def test_out_of_order_merge(self): """Test that revision history is ordered by date, not parent order.""" r = self.open_repo('ooo_merge.git') shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [b'7601d7f6231db6a57f7bbb79ee52e4d462fd44d1', b'f507291b64138b875c28e03469025b1ea20bc614', b'fb5b0425c7ce46959bec94d54b9a157645e114f5', b'f9e39b120c68182a4ba35349f832d0e4e61f485c']) def test_get_tags_empty(self): r = self.open_repo('ooo_merge.git') self.assertEqual({}, r.refs.as_dict(b'refs/tags')) def test_get_config(self): r = self.open_repo('ooo_merge.git') self.assertIsInstance(r.get_config(), Config) def test_get_config_stack(self): r = self.open_repo('ooo_merge.git') self.assertIsInstance(r.get_config_stack(), Config) @skipIf(not getattr(os, 'symlink', None), 'Requires symlink support') def test_submodule(self): temp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) repo_dir = os.path.join(os.path.dirname(__file__), 'data', 'repos') shutil.copytree(os.path.join(repo_dir, 'a.git'), os.path.join(temp_dir, 'a.git'), symlinks=True) rel = os.path.relpath(os.path.join(repo_dir, 'submodule'), temp_dir) os.symlink(os.path.join(rel, 'dotgit'), os.path.join(temp_dir, '.git')) with Repo(temp_dir) as r: self.assertEqual(r.head(), b'a90fa2d900a17e99b433217e988c4eb4a2e9a097') def test_common_revisions(self): """ This test demonstrates that ``find_common_revisions()`` actually returns common heads, not revisions; dulwich already uses ``find_common_revisions()`` in such a manner (see ``Repo.fetch_objects()``). """ expected_shas = set([b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e']) # Source for objects. r_base = self.open_repo('simple_merge.git') # Re-create each-side of the merge in simple_merge.git. # # Since the trees and blobs are missing, the repository created is # corrupted, but we're only checking for commits for the purpose of # this test, so it's immaterial. r1_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, r1_dir) r1_commits = [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', # HEAD b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310'] r2_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, r2_dir) r2_commits = [b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6', # HEAD b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310'] r1 = Repo.init_bare(r1_dir) for c in r1_commits: r1.object_store.add_object(r_base.get_object(c)) r1.refs[b'HEAD'] = r1_commits[0] r2 = Repo.init_bare(r2_dir) for c in r2_commits: r2.object_store.add_object(r_base.get_object(c)) r2.refs[b'HEAD'] = r2_commits[0] # Finally, the 'real' testing! shas = r2.object_store.find_common_revisions(r1.get_graph_walker()) self.assertEqual(set(shas), expected_shas) shas = r1.object_store.find_common_revisions(r2.get_graph_walker()) self.assertEqual(set(shas), expected_shas) def test_shell_hook_pre_commit(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') pre_commit_fail = """#!/bin/sh exit 1 """ pre_commit_success = """#!/bin/sh exit 0 """ repo_dir = os.path.join(self.mkdtemp()) self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) pre_commit = os.path.join(r.controldir(), 'hooks', 'pre-commit') with open(pre_commit, 'w') as f: f.write(pre_commit_fail) os.chmod(pre_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) self.assertRaises(errors.CommitError, r.do_commit, 'failed commit', committer='Test Committer ', author='Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) with open(pre_commit, 'w') as f: f.write(pre_commit_success) os.chmod(pre_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([], r[commit_sha].parents) def test_shell_hook_commit_msg(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') commit_msg_fail = """#!/bin/sh exit 1 """ commit_msg_success = """#!/bin/sh exit 0 """ repo_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) commit_msg = os.path.join(r.controldir(), 'hooks', 'commit-msg') with open(commit_msg, 'w') as f: f.write(commit_msg_fail) os.chmod(commit_msg, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) self.assertRaises(errors.CommitError, r.do_commit, b'failed commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) with open(commit_msg, 'w') as f: f.write(commit_msg_success) os.chmod(commit_msg, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([], r[commit_sha].parents) def test_shell_hook_post_commit(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') repo_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) (fd, path) = tempfile.mkstemp(dir=repo_dir) os.close(fd) post_commit_msg = """#!/bin/sh rm """ + path + """ """ root_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([], r[root_sha].parents) post_commit = os.path.join(r.controldir(), 'hooks', 'post-commit') with open(post_commit, 'wb') as f: f.write(post_commit_msg.encode(locale.getpreferredencoding())) os.chmod(post_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([root_sha], r[commit_sha].parents) self.assertFalse(os.path.exists(path)) post_commit_msg_fail = """#!/bin/sh exit 1 """ with open(post_commit, 'w') as f: f.write(post_commit_msg_fail) os.chmod(post_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) commit_sha2 = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) expected_warning = UserWarning( 'post-commit hook failed: Hook post-commit exited with ' 'non-zero status',) for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) self.assertEqual([commit_sha], r[commit_sha2].parents) def test_as_dict(self): def check(repo): self.assertEqual( repo.refs.subkeys(b'refs/tags'), repo.refs.subkeys(b'refs/tags/')) self.assertEqual( repo.refs.as_dict(b'refs/tags'), repo.refs.as_dict(b'refs/tags/')) self.assertEqual( repo.refs.as_dict(b'refs/heads'), repo.refs.as_dict(b'refs/heads/')) bare = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) with bare.clone(tmp_dir, mkdir=False) as nonbare: check(nonbare) check(bare) def test_working_tree(self): temp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) worktree_temp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, worktree_temp_dir) r = Repo.init(temp_dir) self.addCleanup(r.close) root_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) r.refs[b'refs/heads/master'] = root_sha w = Repo._init_new_working_directory(worktree_temp_dir, r) self.addCleanup(w.close) new_sha = w.do_commit( b'new commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) w.refs[b'HEAD'] = new_sha self.assertEqual(os.path.abspath(r.controldir()), os.path.abspath(w.commondir())) self.assertEqual(r.refs.keys(), w.refs.keys()) self.assertNotEqual(r.head(), w.head()) class BuildRepoRootTests(TestCase): """Tests that build on-disk repos from scratch. Repos live in a temp dir and are torn down after each test. They start with a single commit in master having single file named 'a'. """ def get_repo_dir(self): return os.path.join(tempfile.mkdtemp(), 'test') def setUp(self): super(BuildRepoRootTests, self).setUp() self._repo_dir = self.get_repo_dir() os.makedirs(self._repo_dir) r = self._repo = Repo.init(self._repo_dir) self.addCleanup(tear_down_repo, r) self.assertFalse(r.bare) self.assertEqual(b'ref: refs/heads/master', r.refs.read_ref(b'HEAD')) self.assertRaises(KeyError, lambda: r.refs[b'refs/heads/master']) with open(os.path.join(r.path, 'a'), 'wb') as f: f.write(b'file contents') r.stage(['a']) commit_sha = r.do_commit( b'msg', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([], r[commit_sha].parents) self._root_commit = commit_sha def test_get_shallow(self): self.assertEqual(set(), self._repo.get_shallow()) with open(os.path.join(self._repo.path, '.git', 'shallow'), 'wb') as f: f.write(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097\n') self.assertEqual({b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, self._repo.get_shallow()) def test_update_shallow(self): self._repo.update_shallow(None, None) # no op self.assertEqual(set(), self._repo.get_shallow()) self._repo.update_shallow( [b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'], None) self.assertEqual( {b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, self._repo.get_shallow()) self._repo.update_shallow( [b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'], [b'f9e39b120c68182a4ba35349f832d0e4e61f485c']) self.assertEqual({b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, self._repo.get_shallow()) def test_build_repo(self): r = self._repo self.assertEqual(b'ref: refs/heads/master', r.refs.read_ref(b'HEAD')) self.assertEqual(self._root_commit, r.refs[b'refs/heads/master']) expected_blob = objects.Blob.from_string(b'file contents') self.assertEqual(expected_blob.data, r[expected_blob.id].data) actual_commit = r[self._root_commit] self.assertEqual(b'msg', actual_commit.message) def test_commit_modified(self): r = self._repo with open(os.path.join(r.path, 'a'), 'wb') as f: f.write(b'new contents') r.stage(['a']) commit_sha = r.do_commit( b'modified a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) a_mode, a_id = tree_lookup_path(r.get_object, r[commit_sha].tree, b'a') self.assertEqual(stat.S_IFREG | 0o644, a_mode) self.assertEqual(b'new contents', r[a_id].data) @skipIf(not getattr(os, 'symlink', None), 'Requires symlink support') def test_commit_symlink(self): r = self._repo os.symlink('a', os.path.join(r.path, 'b')) r.stage(['a', 'b']) commit_sha = r.do_commit( b'Symlink b', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) b_mode, b_id = tree_lookup_path(r.get_object, r[commit_sha].tree, b'b') self.assertTrue(stat.S_ISLNK(b_mode)) self.assertEqual(b'a', r[b_id].data) def test_commit_merge_heads_file(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) r = Repo.init(tmp_dir) with open(os.path.join(r.path, 'a'), 'w') as f: f.write('initial text') c1 = r.do_commit( b'initial commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) with open(os.path.join(r.path, 'a'), 'w') as f: f.write('merged text') with open(os.path.join(r.path, '.git', 'MERGE_HEADS'), 'w') as f: f.write('c27a2d21dd136312d7fa9e8baabb82561a1727d0\n') r.stage(['a']) commit_sha = r.do_commit( b'deleted a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([ c1, b'c27a2d21dd136312d7fa9e8baabb82561a1727d0'], r[commit_sha].parents) def test_commit_deleted(self): r = self._repo os.remove(os.path.join(r.path, 'a')) r.stage(['a']) commit_sha = r.do_commit( b'deleted a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) self.assertEqual([], list(r.open_index())) tree = r[r[commit_sha].tree] self.assertEqual([], list(tree.iteritems())) def test_commit_follows(self): r = self._repo r.refs.set_symbolic_ref(b'HEAD', b'refs/heads/bla') commit_sha = r.do_commit( b'commit with strange character', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b'HEAD') self.assertEqual(commit_sha, r[b'refs/heads/bla'].id) def test_commit_encoding(self): r = self._repo commit_sha = r.do_commit( b'commit with strange character \xee', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, encoding=b"iso8859-1") self.assertEqual(b"iso8859-1", r[commit_sha].encoding) def test_compression_level(self): r = self._repo c = r.get_config() c.set(('core',), 'compression', '3') c.set(('core',), 'looseCompression', '4') c.write_to_path() r = Repo(self._repo_dir) self.assertEqual(r.object_store.loose_compression_level, 4) def test_commit_encoding_from_config(self): r = self._repo c = r.get_config() c.set(('i18n',), 'commitEncoding', 'iso8859-1') c.write_to_path() commit_sha = r.do_commit( b'commit with strange character \xee', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual(b"iso8859-1", r[commit_sha].encoding) def test_commit_config_identity(self): # commit falls back to the users' identity if it wasn't specified r = self._repo c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"jelmer@apache.org") c.write_to_path() commit_sha = r.do_commit(b'message') self.assertEqual( b"Jelmer ", r[commit_sha].author) self.assertEqual( b"Jelmer ", r[commit_sha].committer) def test_commit_config_identity_strips_than(self): # commit falls back to the users' identity if it wasn't specified, # and strips superfluous <> r = self._repo c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"") c.write_to_path() commit_sha = r.do_commit(b'message') self.assertEqual( b"Jelmer ", r[commit_sha].author) self.assertEqual( b"Jelmer ", r[commit_sha].committer) def test_commit_config_identity_in_memoryrepo(self): # commit falls back to the users' identity if it wasn't specified r = MemoryRepo.init_bare([], {}) c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"jelmer@apache.org") commit_sha = r.do_commit(b'message', tree=objects.Tree().id) self.assertEqual( b"Jelmer ", r[commit_sha].author) self.assertEqual( b"Jelmer ", r[commit_sha].committer) def overrideEnv(self, name, value): def restore(): if oldval is not None: os.environ[name] = oldval else: del os.environ[name] oldval = os.environ.get(name) os.environ[name] = value self.addCleanup(restore) def test_commit_config_identity_from_env(self): # commit falls back to the users' identity if it wasn't specified self.overrideEnv('GIT_COMMITTER_NAME', 'joe') self.overrideEnv('GIT_COMMITTER_EMAIL', 'joe@example.com') r = self._repo c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"jelmer@apache.org") c.write_to_path() commit_sha = r.do_commit(b'message') self.assertEqual( b"Jelmer ", r[commit_sha].author) self.assertEqual( b"joe ", r[commit_sha].committer) def test_commit_fail_ref(self): r = self._repo def set_if_equals(name, old_ref, new_ref, **kwargs): return False r.refs.set_if_equals = set_if_equals def add_if_new(name, new_ref, **kwargs): self.fail('Unexpected call to add_if_new') r.refs.add_if_new = add_if_new old_shas = set(r.object_store) self.assertRaises(errors.CommitError, r.do_commit, b'failed commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) new_shas = set(r.object_store) - old_shas self.assertEqual(1, len(new_shas)) # Check that the new commit (now garbage) was added. new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual(b'failed commit', new_commit.message) def test_commit_branch(self): r = self._repo commit_sha = r.do_commit( b'commit to branch', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") self.assertEqual(self._root_commit, r[b"HEAD"].id) self.assertEqual(commit_sha, r[b"refs/heads/new_branch"].id) self.assertEqual([], r[commit_sha].parents) self.assertTrue(b"refs/heads/new_branch" in r) new_branch_head = commit_sha commit_sha = r.do_commit( b'commit to branch 2', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") self.assertEqual(self._root_commit, r[b"HEAD"].id) self.assertEqual(commit_sha, r[b"refs/heads/new_branch"].id) self.assertEqual([new_branch_head], r[commit_sha].parents) def test_commit_merge_heads(self): r = self._repo merge_1 = r.do_commit( b'commit to branch 2', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") commit_sha = r.do_commit( b'commit with merge', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, merge_heads=[merge_1]) self.assertEqual( [self._root_commit, merge_1], r[commit_sha].parents) def test_commit_dangling_commit(self): r = self._repo old_shas = set(r.object_store) old_refs = r.get_refs() commit_sha = r.do_commit( b'commit with no ref', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None) new_shas = set(r.object_store) - old_shas # New sha is added, but no new refs self.assertEqual(1, len(new_shas)) new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual([], r[commit_sha].parents) self.assertEqual(old_refs, r.get_refs()) def test_commit_dangling_commit_with_parents(self): r = self._repo old_shas = set(r.object_store) old_refs = r.get_refs() commit_sha = r.do_commit( b'commit with no ref', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None, merge_heads=[self._root_commit]) new_shas = set(r.object_store) - old_shas # New sha is added, but no new refs self.assertEqual(1, len(new_shas)) new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual([self._root_commit], r[commit_sha].parents) self.assertEqual(old_refs, r.get_refs()) def test_stage_absolute(self): r = self._repo os.remove(os.path.join(r.path, 'a')) self.assertRaises(ValueError, r.stage, [os.path.join(r.path, 'a')]) def test_stage_deleted(self): r = self._repo os.remove(os.path.join(r.path, 'a')) r.stage(['a']) r.stage(['a']) # double-stage a deleted path def test_stage_directory(self): r = self._repo os.mkdir(os.path.join(r.path, 'c')) r.stage(['c']) self.assertEqual([b'a'], list(r.open_index())) @skipIf(sys.platform == 'win32', 'tries to implicitly decode as utf8') def test_commit_no_encode_decode(self): r = self._repo - repo_path_bytes = r.path.encode(sys.getfilesystemencoding()) + repo_path_bytes = os.fsencode(r.path) encodings = ('utf8', 'latin1') names = [u'À'.encode(encoding) for encoding in encodings] for name, encoding in zip(names, encodings): full_path = os.path.join(repo_path_bytes, name) with open(full_path, 'wb') as f: f.write(encoding.encode('ascii')) # These files are break tear_down_repo, so cleanup these files # ourselves. self.addCleanup(os.remove, full_path) r.stage(names) commit_sha = r.do_commit( b'Files with different encodings', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None, merge_heads=[self._root_commit]) for name, encoding in zip(names, encodings): mode, id = tree_lookup_path(r.get_object, r[commit_sha].tree, name) self.assertEqual(stat.S_IFREG | 0o644, mode) self.assertEqual(encoding.encode('ascii'), r[id].data) def test_discover_intended(self): path = os.path.join(self._repo_dir, 'b/c') r = Repo.discover(path) self.assertEqual(r.head(), self._repo.head()) def test_discover_isrepo(self): r = Repo.discover(self._repo_dir) self.assertEqual(r.head(), self._repo.head()) def test_discover_notrepo(self): with self.assertRaises(NotGitRepository): Repo.discover('/') class CheckUserIdentityTests(TestCase): def test_valid(self): check_user_identity(b'Me ') def test_invalid(self): self.assertRaises(InvalidUserIdentity, check_user_identity, b'No Email') self.assertRaises(InvalidUserIdentity, check_user_identity, b'Fullname ') self.assertRaises(InvalidUserIdentity, check_user_identity, b'Fullname >order<>')