diff --git a/dulwich/client.py b/dulwich/client.py index 0a0a9811..5a7cca15 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1898 +1,1895 @@ # 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 -try: - from urllib import quote as urlquote - from urllib import unquote as urlunquote -except ImportError: - from urllib.parse import quote as urlquote - from urllib.parse import unquote as urlunquote - -try: - import urlparse -except ImportError: - import urllib.parse as urlparse +from urllib.parse import ( + quote as urlquote, + unquote as urlunquote, + urlparse, + urljoin, + urlunparse, + urlunsplit, + ) 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.urlparse() + 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 urlparse.urlunsplit(("git", netloc, path, '', '')) + 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 urlparse.urlunsplit(('file', '', 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()) 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 urlparse.urlunsplit(('ssh', netloc, path, '', '')) + 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(urlparse.urlunparse(parsedurl), **kwargs) + 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 urlparse.urljoin(self._base_url, path).rstrip("/") + "/" + 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 = urlparse.urljoin(base_url, tail) + 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 = urlparse.urljoin(url, service) + 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.urlparse(url) + 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 eb96d2e9..cc87f546 100644 --- a/dulwich/contrib/swift.py +++ b/dulwich/contrib/swift.py @@ -1,1058 +1,1047 @@ # 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 -try: - import urlparse -except ImportError: - import urllib.parse as urlparse +import urllib.parse as urlparse from io import BytesIO -try: - from ConfigParser import ConfigParser -except ImportError: - from configparser import ConfigParser +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, ) -try: - from simplejson import loads as json_loads - from simplejson import dumps as json_dumps -except ImportError: - from json import loads as json_loads - from json import dumps as json_dumps +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)) + 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())) + 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) + 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()) + 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) + 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())) 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/contrib/test_swift.py b/dulwich/contrib/test_swift.py index 5891b735..043d452e 100644 --- a/dulwich/contrib/test_swift.py +++ b/dulwich/contrib/test_swift.py @@ -1,477 +1,470 @@ # test_swift.py -- Unittests for the Swift backend. # 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. # """Tests for dulwich.contrib.swift.""" import posixpath from time import time -from io import BytesIO -try: - from StringIO import StringIO -except ImportError: - from io import StringIO +from io import BytesIO, StringIO from unittest import skipIf from dulwich.tests import ( TestCase, ) from dulwich.tests.test_object_store import ( ObjectStoreTests, ) from dulwich.objects import ( Blob, Commit, Tree, Tag, parse_timezone, ) -try: - from simplejson import dumps as json_dumps -except ImportError: - from json import dumps as json_dumps +import json missing_libs = [] try: import gevent # noqa:F401 except ImportError: missing_libs.append("gevent") try: import geventhttpclient # noqa:F401 except ImportError: missing_libs.append("geventhttpclient") try: from mock import patch except ImportError: missing_libs.append("mock") skipmsg = "Required libraries are not installed (%r)" % missing_libs if not missing_libs: from dulwich.contrib import swift config_file = """[swift] auth_url = http://127.0.0.1:8080/auth/%(version_str)s auth_ver = %(version_int)s username = test;tester password = testing region_name = %(region_name)s endpoint_type = %(endpoint_type)s concurrency = %(concurrency)s chunk_length = %(chunk_length)s cache_length = %(cache_length)s http_pool_length = %(http_pool_length)s http_timeout = %(http_timeout)s """ def_config_file = {'version_str': 'v1.0', 'version_int': 1, 'concurrency': 1, 'chunk_length': 12228, 'cache_length': 1, 'region_name': 'test', 'endpoint_type': 'internalURL', 'http_pool_length': 1, 'http_timeout': 1} def create_swift_connector(store={}): return lambda root, conf: FakeSwiftConnector(root, conf=conf, store=store) class Response(object): def __init__(self, headers={}, status=200, content=None): self.headers = headers self.status_code = status self.content = content def __getitem__(self, key): return self.headers[key] def items(self): return self.headers.items() def read(self): return self.content def fake_auth_request_v1(*args, **kwargs): ret = Response({'X-Storage-Url': 'http://127.0.0.1:8080/v1.0/AUTH_fakeuser', 'X-Auth-Token': '12' * 10}, 200) return ret def fake_auth_request_v1_error(*args, **kwargs): ret = Response({}, 401) return ret def fake_auth_request_v2(*args, **kwargs): s_url = 'http://127.0.0.1:8080/v1.0/AUTH_fakeuser' resp = {'access': {'token': {'id': '12' * 10}, 'serviceCatalog': [ {'type': 'object-store', 'endpoints': [{'region': 'test', 'internalURL': s_url, }, ] }, ] } } - ret = Response(status=200, content=json_dumps(resp)) + ret = Response(status=200, content=json.dumps(resp)) return ret def create_commit(data, marker=b'Default', blob=None): if not blob: blob = Blob.from_string(b'The blob content ' + marker) tree = Tree() tree.add(b"thefile_" + marker, 0o100644, blob.id) cmt = Commit() if data: assert isinstance(data[-1], Commit) cmt.parents = [data[-1].id] cmt.tree = tree.id author = b"John Doe " + marker + b" " cmt.author = cmt.committer = author tz = parse_timezone(b'-0200')[0] cmt.commit_time = cmt.author_time = int(time()) cmt.commit_timezone = cmt.author_timezone = tz cmt.encoding = b"UTF-8" cmt.message = b"The commit message " + marker tag = Tag() tag.tagger = b"john@doe.net" tag.message = b"Annotated tag" tag.tag_timezone = parse_timezone(b'-0200')[0] tag.tag_time = cmt.author_time tag.object = (Commit, cmt.id) tag.name = b"v_" + marker + b"_0.1" return blob, tree, tag, cmt def create_commits(length=1, marker=b'Default'): data = [] for i in range(0, length): _marker = ("%s_%s" % (marker, i)).encode() blob, tree, tag, cmt = create_commit(data, _marker) data.extend([blob, tree, tag, cmt]) return data @skipIf(missing_libs, skipmsg) class FakeSwiftConnector(object): def __init__(self, root, conf, store=None): if store: self.store = store else: self.store = {} self.conf = conf self.root = root self.concurrency = 1 self.chunk_length = 12228 self.cache_length = 1 def put_object(self, name, content): name = posixpath.join(self.root, name) if hasattr(content, 'seek'): content.seek(0) content = content.read() self.store[name] = content def get_object(self, name, range=None): name = posixpath.join(self.root, name) if not range: try: return BytesIO(self.store[name]) except KeyError: return None else: l, r = range.split('-') try: if not l: r = -int(r) return self.store[name][r:] else: return self.store[name][int(l):int(r)] except KeyError: return None def get_container_objects(self): return [{'name': k.replace(self.root + '/', '')} for k in self.store] def create_root(self): if self.root in self.store.keys(): pass else: self.store[self.root] = '' def get_object_stat(self, name): name = posixpath.join(self.root, name) if name not in self.store: return None return {'content-length': len(self.store[name])} @skipIf(missing_libs, skipmsg) class TestSwiftRepo(TestCase): def setUp(self): super(TestSwiftRepo, self).setUp() self.conf = swift.load_conf(file=StringIO(config_file % def_config_file)) def test_init(self): store = {'fakerepo/objects/pack': ''} with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=store): swift.SwiftRepo('fakerepo', conf=self.conf) def test_init_no_data(self): with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector): self.assertRaises(Exception, swift.SwiftRepo, 'fakerepo', self.conf) def test_init_bad_data(self): store = {'fakerepo/.git/objects/pack': ''} with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=store): self.assertRaises(Exception, swift.SwiftRepo, 'fakerepo', self.conf) def test_put_named_file(self): store = {'fakerepo/objects/pack': ''} with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=store): repo = swift.SwiftRepo('fakerepo', conf=self.conf) desc = b'Fake repo' repo._put_named_file('description', desc) self.assertEqual(repo.scon.store['fakerepo/description'], desc) def test_init_bare(self): fsc = FakeSwiftConnector('fakeroot', conf=self.conf) with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=fsc.store): swift.SwiftRepo.init_bare(fsc, conf=self.conf) self.assertIn('fakeroot/objects/pack', fsc.store) self.assertIn('fakeroot/info/refs', fsc.store) self.assertIn('fakeroot/description', fsc.store) @skipIf(missing_libs, skipmsg) class TestSwiftInfoRefsContainer(TestCase): def setUp(self): super(TestSwiftInfoRefsContainer, self).setUp() content = ( b"22effb216e3a82f97da599b8885a6cadb488b4c5\trefs/heads/master\n" b"cca703b0e1399008b53a1a236d6b4584737649e4\trefs/heads/dev") self.store = {'fakerepo/info/refs': content} self.conf = swift.load_conf(file=StringIO(config_file % def_config_file)) self.fsc = FakeSwiftConnector('fakerepo', conf=self.conf) self.object_store = {} def test_init(self): """info/refs does not exists""" irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) self.assertEqual(len(irc._refs), 0) self.fsc.store = self.store irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) self.assertIn(b'refs/heads/dev', irc.allkeys()) self.assertIn(b'refs/heads/master', irc.allkeys()) def test_set_if_equals(self): self.fsc.store = self.store irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) irc.set_if_equals(b'refs/heads/dev', b"cca703b0e1399008b53a1a236d6b4584737649e4", b'1'*40) self.assertEqual(irc[b'refs/heads/dev'], b'1'*40) def test_remove_if_equals(self): self.fsc.store = self.store irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) irc.remove_if_equals(b'refs/heads/dev', b"cca703b0e1399008b53a1a236d6b4584737649e4") self.assertNotIn(b'refs/heads/dev', irc.allkeys()) @skipIf(missing_libs, skipmsg) class TestSwiftConnector(TestCase): def setUp(self): super(TestSwiftConnector, self).setUp() self.conf = swift.load_conf(file=StringIO(config_file % def_config_file)) with patch('geventhttpclient.HTTPClient.request', fake_auth_request_v1): self.conn = swift.SwiftConnector('fakerepo', conf=self.conf) def test_init_connector(self): self.assertEqual(self.conn.auth_ver, '1') self.assertEqual(self.conn.auth_url, 'http://127.0.0.1:8080/auth/v1.0') self.assertEqual(self.conn.user, 'test:tester') self.assertEqual(self.conn.password, 'testing') self.assertEqual(self.conn.root, 'fakerepo') self.assertEqual(self.conn.storage_url, 'http://127.0.0.1:8080/v1.0/AUTH_fakeuser') self.assertEqual(self.conn.token, '12' * 10) self.assertEqual(self.conn.http_timeout, 1) self.assertEqual(self.conn.http_pool_length, 1) self.assertEqual(self.conn.concurrency, 1) self.conf.set('swift', 'auth_ver', '2') self.conf.set('swift', 'auth_url', 'http://127.0.0.1:8080/auth/v2.0') with patch('geventhttpclient.HTTPClient.request', fake_auth_request_v2): conn = swift.SwiftConnector('fakerepo', conf=self.conf) self.assertEqual(conn.user, 'tester') self.assertEqual(conn.tenant, 'test') self.conf.set('swift', 'auth_ver', '1') self.conf.set('swift', 'auth_url', 'http://127.0.0.1:8080/auth/v1.0') with patch('geventhttpclient.HTTPClient.request', fake_auth_request_v1_error): self.assertRaises(swift.SwiftException, lambda: swift.SwiftConnector('fakerepo', conf=self.conf)) def test_root_exists(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.test_root_exists(), True) def test_root_not_exists(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertEqual(self.conn.test_root_exists(), None) def test_create_root(self): with patch('dulwich.contrib.swift.SwiftConnector.test_root_exists', lambda *args: None): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.create_root(), None) def test_create_root_fails(self): with patch('dulwich.contrib.swift.SwiftConnector.test_root_exists', lambda *args: None): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertRaises(swift.SwiftException, lambda: self.conn.create_root()) def test_get_container_objects(self): with patch('geventhttpclient.HTTPClient.request', - lambda *args: Response(content=json_dumps( + lambda *args: Response(content=json.dumps( (({'name': 'a'}, {'name': 'b'}))))): self.assertEqual(len(self.conn.get_container_objects()), 2) def test_get_container_objects_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertEqual(self.conn.get_container_objects(), None) def test_get_object_stat(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(headers={'content-length': '10'})): self.assertEqual(self.conn.get_object_stat('a')['content-length'], '10') def test_get_object_stat_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertEqual(self.conn.get_object_stat('a'), None) def test_put_object(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response()): self.assertEqual(self.conn.put_object('a', BytesIO(b'content')), None) def test_put_object_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(status=400)): self.assertRaises(swift.SwiftException, lambda: self.conn.put_object( 'a', BytesIO(b'content'))) def test_get_object(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(content=b'content')): self.assertEqual(self.conn.get_object('a').read(), b'content') with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(content=b'content')): self.assertEqual( self.conn.get_object('a', range='0-6'), b'content') def test_get_object_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(status=404)): self.assertEqual(self.conn.get_object('a'), None) def test_del_object(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.del_object('a'), None) def test_del_root(self): with patch('dulwich.contrib.swift.SwiftConnector.del_object', lambda *args: None): with patch('dulwich.contrib.swift.SwiftConnector.' 'get_container_objects', lambda *args: ({'name': 'a'}, {'name': 'b'})): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.del_root(), None) @skipIf(missing_libs, skipmsg) class SwiftObjectStoreTests(ObjectStoreTests, TestCase): def setUp(self): TestCase.setUp(self) conf = swift.load_conf(file=StringIO(config_file % def_config_file)) fsc = FakeSwiftConnector('fakerepo', conf=conf) self.store = swift.SwiftObjectStore(fsc) diff --git a/dulwich/objects.py b/dulwich/objects.py index 59f6b85c..ed062390 100644 --- a/dulwich/objects.py +++ b/dulwich/objects.py @@ -1,1434 +1,1434 @@ # objects.py -- Access to base git objects # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Access to base git objects.""" import binascii from io import BytesIO from collections import namedtuple import os import posixpath import stat import warnings import zlib from hashlib import sha1 from dulwich.errors import ( ChecksumMismatch, NotBlobError, NotCommitError, NotTagError, NotTreeError, ObjectFormatException, FileFormatException, ) from dulwich.file import GitFile ZERO_SHA = b'0' * 40 # Header fields for commits _TREE_HEADER = b'tree' _PARENT_HEADER = b'parent' _AUTHOR_HEADER = b'author' _COMMITTER_HEADER = b'committer' _ENCODING_HEADER = b'encoding' _MERGETAG_HEADER = b'mergetag' _GPGSIG_HEADER = b'gpgsig' # Header fields for objects _OBJECT_HEADER = b'object' _TYPE_HEADER = b'type' _TAG_HEADER = b'tag' _TAGGER_HEADER = b'tagger' S_IFGITLINK = 0o160000 MAX_TIME = 9223372036854775807 # (2**63) - 1 - signed long int max BEGIN_PGP_SIGNATURE = b"-----BEGIN PGP SIGNATURE-----" class EmptyFileException(FileFormatException): """An unexpectedly empty file was encountered.""" def S_ISGITLINK(m): """Check if a mode indicates a submodule. Args: m: Mode to check Returns: a ``boolean`` """ return (stat.S_IFMT(m) == S_IFGITLINK) def _decompress(string): dcomp = zlib.decompressobj() dcomped = dcomp.decompress(string) dcomped += dcomp.flush() return dcomped def sha_to_hex(sha): """Takes a string and returns the hex of the sha within""" hexsha = binascii.hexlify(sha) assert len(hexsha) == 40, "Incorrect length of sha1 string: %d" % hexsha return hexsha def hex_to_sha(hex): """Takes a hex sha and returns a binary sha""" assert len(hex) == 40, "Incorrect length of hexsha: %s" % hex try: return binascii.unhexlify(hex) except TypeError as exc: if not isinstance(hex, bytes): raise raise ValueError(exc.args[0]) def valid_hexsha(hex): if len(hex) != 40: return False try: binascii.unhexlify(hex) except (TypeError, binascii.Error): return False else: return True def hex_to_filename(path, hex): """Takes a hex sha and returns its filename relative to the given path.""" # os.path.join accepts bytes or unicode, but all args must be of the same # type. Make sure that hex which is expected to be bytes, is the same type # as path. if getattr(path, 'encode', None) is not None: hex = hex.decode('ascii') dir = hex[:2] file = hex[2:] # Check from object dir return os.path.join(path, dir, file) def filename_to_hex(filename): """Takes an object filename and returns its corresponding hex sha.""" # grab the last (up to) two path components names = filename.rsplit(os.path.sep, 2)[-2:] errmsg = "Invalid object filename: %s" % filename assert len(names) == 2, errmsg base, rest = names assert len(base) == 2 and len(rest) == 38, errmsg hex = (base + rest).encode('ascii') hex_to_sha(hex) return hex def object_header(num_type, length): """Return an object header for the given numeric type and text length.""" return (object_class(num_type).type_name + b' ' + str(length).encode('ascii') + b'\0') def serializable_property(name, docstring=None): """A property that helps tracking whether serialization is necessary. """ def set(obj, value): setattr(obj, "_"+name, value) obj._needs_serialization = True def get(obj): return getattr(obj, "_"+name) return property(get, set, doc=docstring) def object_class(type): """Get the object class corresponding to the given type. Args: type: Either a type name string or a numeric type. Returns: The ShaFile subclass corresponding to the given type, or None if type is not a valid type name/number. """ return _TYPE_MAP.get(type, None) def check_hexsha(hex, error_msg): """Check if a string is a valid hex sha string. Args: hex: Hex string to check error_msg: Error message to use in exception Raises: ObjectFormatException: Raised when the string is not valid """ if not valid_hexsha(hex): raise ObjectFormatException("%s %s" % (error_msg, hex)) def check_identity(identity, error_msg): """Check if the specified identity is valid. This will raise an exception if the identity is not valid. Args: identity: Identity string error_msg: Error message to use in exception """ email_start = identity.find(b'<') email_end = identity.find(b'>') if (email_start < 0 or email_end < 0 or email_end <= email_start or identity.find(b'<', email_start + 1) >= 0 or identity.find(b'>', email_end + 1) >= 0 or not identity.endswith(b'>')): raise ObjectFormatException(error_msg) def check_time(time_seconds): """Check if the specified time is not prone to overflow error. This will raise an exception if the time is not valid. Args: time_info: author/committer/tagger info """ # Prevent overflow error if time_seconds > MAX_TIME: raise ObjectFormatException( 'Date field should not exceed %s' % MAX_TIME) def git_line(*items): """Formats items into a space separated line.""" return b' '.join(items) + b'\n' class FixedSha(object): """SHA object that behaves like hashlib's but is given a fixed value.""" __slots__ = ('_hexsha', '_sha') def __init__(self, hexsha): if getattr(hexsha, 'encode', None) is not None: hexsha = hexsha.encode('ascii') if not isinstance(hexsha, bytes): raise TypeError('Expected bytes for hexsha, got %r' % hexsha) self._hexsha = hexsha self._sha = hex_to_sha(hexsha) def digest(self): """Return the raw SHA digest.""" return self._sha def hexdigest(self): """Return the hex SHA digest.""" return self._hexsha.decode('ascii') class ShaFile(object): """A git SHA file.""" __slots__ = ('_chunked_text', '_sha', '_needs_serialization') @staticmethod def _parse_legacy_object_header(magic, f): """Parse a legacy object, creating it but not reading the file.""" bufsize = 1024 decomp = zlib.decompressobj() header = decomp.decompress(magic) start = 0 end = -1 while end < 0: extra = f.read(bufsize) header += decomp.decompress(extra) magic += extra end = header.find(b'\0', start) start = len(header) header = header[:end] type_name, size = header.split(b' ', 1) try: int(size) # sanity check except ValueError as e: raise ObjectFormatException("Object size not an integer: %s" % e) obj_class = object_class(type_name) if not obj_class: raise ObjectFormatException("Not a known type: %s" % type_name) return obj_class() def _parse_legacy_object(self, map): """Parse a legacy object, setting the raw string.""" text = _decompress(map) header_end = text.find(b'\0') if header_end < 0: raise ObjectFormatException("Invalid object header, no \\0") self.set_raw_string(text[header_end+1:]) def as_legacy_object_chunks(self, compression_level=-1): """Return chunks representing the object in the experimental format. Returns: List of strings """ compobj = zlib.compressobj(compression_level) yield compobj.compress(self._header()) for chunk in self.as_raw_chunks(): yield compobj.compress(chunk) yield compobj.flush() def as_legacy_object(self, compression_level=-1): """Return string representing the object in the experimental format. """ return b''.join(self.as_legacy_object_chunks( compression_level=compression_level)) def as_raw_chunks(self): """Return chunks with serialization of the object. Returns: List of strings, not necessarily one per line """ if self._needs_serialization: self._sha = None self._chunked_text = self._serialize() self._needs_serialization = False return self._chunked_text def as_raw_string(self): """Return raw string with serialization of the object. Returns: String object """ return b''.join(self.as_raw_chunks()) def __bytes__(self): """Return raw string serialization of this object.""" return self.as_raw_string() def __hash__(self): """Return unique hash for this object.""" return hash(self.id) def as_pretty_string(self): """Return a string representing this object, fit for display.""" return self.as_raw_string() def set_raw_string(self, text, sha=None): """Set the contents of this object from a serialized string.""" if not isinstance(text, bytes): raise TypeError('Expected bytes for text, got %r' % text) self.set_raw_chunks([text], sha) def set_raw_chunks(self, chunks, sha=None): """Set the contents of this object from a list of chunks.""" self._chunked_text = chunks self._deserialize(chunks) if sha is None: self._sha = None else: self._sha = FixedSha(sha) self._needs_serialization = False @staticmethod def _parse_object_header(magic, f): """Parse a new style object, creating it but not reading the file.""" num_type = (ord(magic[0:1]) >> 4) & 7 obj_class = object_class(num_type) if not obj_class: raise ObjectFormatException("Not a known type %d" % num_type) return obj_class() def _parse_object(self, map): """Parse a new style object, setting self._text.""" # skip type and size; type must have already been determined, and # we trust zlib to fail if it's otherwise corrupted byte = ord(map[0:1]) used = 1 while (byte & 0x80) != 0: byte = ord(map[used:used+1]) used += 1 raw = map[used:] self.set_raw_string(_decompress(raw)) @classmethod def _is_legacy_object(cls, magic): b0 = ord(magic[0:1]) b1 = ord(magic[1:2]) word = (b0 << 8) + b1 return (b0 & 0x8F) == 0x08 and (word % 31) == 0 @classmethod def _parse_file(cls, f): map = f.read() if not map: raise EmptyFileException('Corrupted empty file detected') if cls._is_legacy_object(map): obj = cls._parse_legacy_object_header(map, f) obj._parse_legacy_object(map) else: obj = cls._parse_object_header(map, f) obj._parse_object(map) return obj def __init__(self): """Don't call this directly""" self._sha = None self._chunked_text = [] self._needs_serialization = True def _deserialize(self, chunks): raise NotImplementedError(self._deserialize) def _serialize(self): raise NotImplementedError(self._serialize) @classmethod def from_path(cls, path): """Open a SHA file from disk.""" with GitFile(path, 'rb') as f: return cls.from_file(f) @classmethod def from_file(cls, f): """Get the contents of a SHA file on disk.""" try: obj = cls._parse_file(f) obj._sha = None return obj except (IndexError, ValueError): raise ObjectFormatException("invalid object header") @staticmethod def from_raw_string(type_num, string, sha=None): """Creates an object of the indicated type from the raw string given. Args: type_num: The numeric type of the object. string: The raw uncompressed contents. sha: Optional known sha for the object """ obj = object_class(type_num)() obj.set_raw_string(string, sha) return obj @staticmethod def from_raw_chunks(type_num, chunks, sha=None): """Creates an object of the indicated type from the raw chunks given. Args: type_num: The numeric type of the object. chunks: An iterable of the raw uncompressed contents. sha: Optional known sha for the object """ obj = object_class(type_num)() obj.set_raw_chunks(chunks, sha) return obj @classmethod def from_string(cls, string): """Create a ShaFile from a string.""" obj = cls() obj.set_raw_string(string) return obj def _check_has_member(self, member, error_msg): """Check that the object has a given member variable. Args: member: the member variable to check for error_msg: the message for an error if the member is missing Raises: ObjectFormatException: with the given error_msg if member is missing or is None """ if getattr(self, member, None) is None: raise ObjectFormatException(error_msg) def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way ChecksumMismatch: if the object was created with a SHA that does not match its contents """ # TODO: if we find that error-checking during object parsing is a # performance bottleneck, those checks should be moved to the class's # check() method during optimization so we can still check the object # when necessary. old_sha = self.id try: self._deserialize(self.as_raw_chunks()) self._sha = None new_sha = self.id except Exception as e: raise ObjectFormatException(e) if old_sha != new_sha: raise ChecksumMismatch(new_sha, old_sha) def _header(self): return object_header(self.type, self.raw_length()) def raw_length(self): """Returns the length of the raw string of this object.""" ret = 0 for chunk in self.as_raw_chunks(): ret += len(chunk) return ret def sha(self): """The SHA1 object that is the name of this object.""" if self._sha is None or self._needs_serialization: # this is a local because as_raw_chunks() overwrites self._sha new_sha = sha1() new_sha.update(self._header()) for chunk in self.as_raw_chunks(): new_sha.update(chunk) self._sha = new_sha return self._sha def copy(self): """Create a new copy of this SHA1 object from its raw string""" obj_class = object_class(self.get_type()) return obj_class.from_raw_string( self.get_type(), self.as_raw_string(), self.id) @property def id(self): """The hex SHA of this object.""" return self.sha().hexdigest().encode('ascii') def get_type(self): """Return the type number for this object class.""" return self.type_num def set_type(self, type): """Set the type number for this object class.""" self.type_num = type # DEPRECATED: use type_num or type_name as needed. type = property(get_type, set_type) def __repr__(self): return "<%s %s>" % (self.__class__.__name__, self.id) def __ne__(self, other): """Check whether this object does not match the other.""" return not isinstance(other, ShaFile) or self.id != other.id def __eq__(self, other): """Return True if the SHAs of the two objects match. """ return isinstance(other, ShaFile) and self.id == other.id def __lt__(self, other): """Return whether SHA of this object is less than the other. """ if not isinstance(other, ShaFile): raise TypeError return self.id < other.id def __le__(self, other): """Check whether SHA of this object is less than or equal to the other. """ if not isinstance(other, ShaFile): raise TypeError return self.id <= other.id def __cmp__(self, other): """Compare the SHA of this object with that of the other object. """ if not isinstance(other, ShaFile): raise TypeError return cmp(self.id, other.id) # noqa: F821 class Blob(ShaFile): """A Git Blob object.""" __slots__ = () type_name = b'blob' type_num = 3 def __init__(self): super(Blob, self).__init__() self._chunked_text = [] self._needs_serialization = False def _get_data(self): return self.as_raw_string() def _set_data(self, data): self.set_raw_string(data) data = property(_get_data, _set_data, - "The text contained within the blob object.") + doc="The text contained within the blob object.") def _get_chunked(self): return self._chunked_text def _set_chunked(self, chunks): self._chunked_text = chunks def _serialize(self): return self._chunked_text def _deserialize(self, chunks): self._chunked_text = chunks chunked = property( _get_chunked, _set_chunked, - "The text within the blob object, as chunks (not necessarily lines).") + doc="The text in the blob object, as chunks (not necessarily lines)") @classmethod def from_path(cls, path): blob = ShaFile.from_path(path) if not isinstance(blob, cls): raise NotBlobError(path) return blob def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way """ super(Blob, self).check() def splitlines(self): """Return list of lines in this blob. This preserves the original line endings. """ chunks = self.chunked if not chunks: return [] if len(chunks) == 1: return chunks[0].splitlines(True) remaining = None ret = [] for chunk in chunks: lines = chunk.splitlines(True) if len(lines) > 1: ret.append((remaining or b"") + lines[0]) ret.extend(lines[1:-1]) remaining = lines[-1] elif len(lines) == 1: if remaining is None: remaining = lines.pop() else: remaining += lines.pop() if remaining is not None: ret.append(remaining) return ret def _parse_message(chunks): """Parse a message with a list of fields and a body. Args: chunks: the raw chunks of the tag or commit object. Returns: iterator of tuples of (field, value), one per header line, in the order read from the text, possibly including duplicates. Includes a field named None for the freeform tag/commit text. """ f = BytesIO(b''.join(chunks)) k = None v = "" eof = False def _strip_last_newline(value): """Strip the last newline from value""" if value and value.endswith(b'\n'): return value[:-1] return value # Parse the headers # # Headers can contain newlines. The next line is indented with a space. # We store the latest key as 'k', and the accumulated value as 'v'. for line in f: if line.startswith(b' '): # Indented continuation of the previous line v += line[1:] else: if k is not None: # We parsed a new header, return its value yield (k, _strip_last_newline(v)) if line == b'\n': # Empty line indicates end of headers break (k, v) = line.split(b' ', 1) else: # We reached end of file before the headers ended. We still need to # return the previous header, then we need to return a None field for # the text. eof = True if k is not None: yield (k, _strip_last_newline(v)) yield (None, None) if not eof: # We didn't reach the end of file while parsing headers. We can return # the rest of the file as a message. yield (None, f.read()) f.close() class Tag(ShaFile): """A Git Tag object.""" type_name = b'tag' type_num = 4 __slots__ = ('_tag_timezone_neg_utc', '_name', '_object_sha', '_object_class', '_tag_time', '_tag_timezone', '_tagger', '_message', '_signature') def __init__(self): super(Tag, self).__init__() self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False self._signature = None @classmethod def from_path(cls, filename): tag = ShaFile.from_path(filename) if not isinstance(tag, cls): raise NotTagError(filename) return tag def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way """ super(Tag, self).check() self._check_has_member("_object_sha", "missing object sha") self._check_has_member("_object_class", "missing object type") self._check_has_member("_name", "missing tag name") if not self._name: raise ObjectFormatException("empty tag name") check_hexsha(self._object_sha, "invalid object sha") if getattr(self, "_tagger", None): check_identity(self._tagger, "invalid tagger") self._check_has_member("_tag_time", "missing tag time") check_time(self._tag_time) last = None for field, _ in _parse_message(self._chunked_text): if field == _OBJECT_HEADER and last is not None: raise ObjectFormatException("unexpected object") elif field == _TYPE_HEADER and last != _OBJECT_HEADER: raise ObjectFormatException("unexpected type") elif field == _TAG_HEADER and last != _TYPE_HEADER: raise ObjectFormatException("unexpected tag name") elif field == _TAGGER_HEADER and last != _TAG_HEADER: raise ObjectFormatException("unexpected tagger") last = field def _serialize(self): chunks = [] chunks.append(git_line(_OBJECT_HEADER, self._object_sha)) chunks.append(git_line(_TYPE_HEADER, self._object_class.type_name)) chunks.append(git_line(_TAG_HEADER, self._name)) if self._tagger: if self._tag_time is None: chunks.append(git_line(_TAGGER_HEADER, self._tagger)) else: chunks.append(git_line( _TAGGER_HEADER, self._tagger, str(self._tag_time).encode('ascii'), format_timezone( self._tag_timezone, self._tag_timezone_neg_utc))) if self._message is not None: chunks.append(b'\n') # To close headers chunks.append(self._message) if self._signature is not None: chunks.append(self._signature) return chunks def _deserialize(self, chunks): """Grab the metadata attached to the tag""" self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False for field, value in _parse_message(chunks): if field == _OBJECT_HEADER: self._object_sha = value elif field == _TYPE_HEADER: obj_class = object_class(value) if not obj_class: raise ObjectFormatException("Not a known type: %s" % value) self._object_class = obj_class elif field == _TAG_HEADER: self._name = value elif field == _TAGGER_HEADER: (self._tagger, self._tag_time, (self._tag_timezone, self._tag_timezone_neg_utc)) = parse_time_entry(value) elif field is None: if value is None: self._message = None self._signature = None else: try: sig_idx = value.index(BEGIN_PGP_SIGNATURE) except ValueError: self._message = value self._signature = None else: self._message = value[:sig_idx] self._signature = value[sig_idx:] else: raise ObjectFormatException("Unknown field %s" % field) def _get_object(self): """Get the object pointed to by this tag. Returns: tuple of (object class, sha). """ return (self._object_class, self._object_sha) def _set_object(self, value): (self._object_class, self._object_sha) = value self._needs_serialization = True object = property(_get_object, _set_object) name = serializable_property("name", "The name of this tag") tagger = serializable_property( "tagger", "Returns the name of the person who created this tag") tag_time = serializable_property( "tag_time", "The creation timestamp of the tag. As the number of seconds " "since the epoch") tag_timezone = serializable_property( "tag_timezone", "The timezone that tag_time is in.") message = serializable_property( "message", "the message attached to this tag") signature = serializable_property( "signature", "Optional detached GPG signature") class TreeEntry(namedtuple('TreeEntry', ['path', 'mode', 'sha'])): """Named tuple encapsulating a single tree entry.""" def in_path(self, path): """Return a copy of this entry with the given path prepended.""" if not isinstance(self.path, bytes): raise TypeError('Expected bytes for path, got %r' % path) return TreeEntry(posixpath.join(path, self.path), self.mode, self.sha) def parse_tree(text, strict=False): """Parse a tree text. Args: text: Serialized text to parse Returns: iterator of tuples of (name, mode, sha) Raises: ObjectFormatException: if the object was malformed in some way """ count = 0 length = len(text) while count < length: mode_end = text.index(b' ', count) mode_text = text[count:mode_end] if strict and mode_text.startswith(b'0'): raise ObjectFormatException("Invalid mode '%s'" % mode_text) try: mode = int(mode_text, 8) except ValueError: raise ObjectFormatException("Invalid mode '%s'" % mode_text) name_end = text.index(b'\0', mode_end) name = text[mode_end+1:name_end] count = name_end+21 sha = text[name_end+1:count] if len(sha) != 20: raise ObjectFormatException("Sha has invalid length") hexsha = sha_to_hex(sha) yield (name, mode, hexsha) def serialize_tree(items): """Serialize the items in a tree to a text. Args: items: Sorted iterable over (name, mode, sha) tuples Returns: Serialized tree text as chunks """ for name, mode, hexsha in items: yield (("%04o" % mode).encode('ascii') + b' ' + name + b'\0' + hex_to_sha(hexsha)) def sorted_tree_items(entries, name_order): """Iterate over a tree entries dictionary. Args: name_order: If True, iterate entries in order of their name. If False, iterate entries in tree order, that is, treat subtree entries as having '/' appended. entries: Dictionary mapping names to (mode, sha) tuples Returns: Iterator over (name, mode, hexsha) """ key_func = name_order and key_entry_name_order or key_entry for name, entry in sorted(entries.items(), key=key_func): mode, hexsha = entry # Stricter type checks than normal to mirror checks in the C version. mode = int(mode) if not isinstance(hexsha, bytes): raise TypeError('Expected bytes for SHA, got %r' % hexsha) yield TreeEntry(name, mode, hexsha) def key_entry(entry): """Sort key for tree entry. Args: entry: (name, value) tuplee """ (name, value) = entry if stat.S_ISDIR(value[0]): name += b'/' return name def key_entry_name_order(entry): """Sort key for tree entry in name order.""" return entry[0] def pretty_format_tree_entry(name, mode, hexsha, encoding="utf-8"): """Pretty format tree entry. Args: name: Name of the directory entry mode: Mode of entry hexsha: Hexsha of the referenced object Returns: string describing the tree entry """ if mode & stat.S_IFDIR: kind = "tree" else: kind = "blob" return "%04o %s %s\t%s\n" % ( mode, kind, hexsha.decode('ascii'), name.decode(encoding, 'replace')) class Tree(ShaFile): """A Git tree object""" type_name = b'tree' type_num = 2 __slots__ = ('_entries') def __init__(self): super(Tree, self).__init__() self._entries = {} @classmethod def from_path(cls, filename): tree = ShaFile.from_path(filename) if not isinstance(tree, cls): raise NotTreeError(filename) return tree def __contains__(self, name): return name in self._entries def __getitem__(self, name): return self._entries[name] def __setitem__(self, name, value): """Set a tree entry by name. Args: name: The name of the entry, as a string. value: A tuple of (mode, hexsha), where mode is the mode of the entry as an integral type and hexsha is the hex SHA of the entry as a string. """ mode, hexsha = value self._entries[name] = (mode, hexsha) self._needs_serialization = True def __delitem__(self, name): del self._entries[name] self._needs_serialization = True def __len__(self): return len(self._entries) def __iter__(self): return iter(self._entries) def add(self, name, mode, hexsha): """Add an entry to the tree. Args: mode: The mode of the entry as an integral type. Not all possible modes are supported by git; see check() for details. name: The name of the entry, as a string. hexsha: The hex SHA of the entry as a string. """ if isinstance(name, int) and isinstance(mode, bytes): (name, mode) = (mode, name) warnings.warn( "Please use Tree.add(name, mode, hexsha)", category=DeprecationWarning, stacklevel=2) self._entries[name] = mode, hexsha self._needs_serialization = True def iteritems(self, name_order=False): """Iterate over entries. Args: name_order: If True, iterate in name order instead of tree order. Returns: Iterator over (name, mode, sha) tuples """ return sorted_tree_items(self._entries, name_order) def items(self): """Return the sorted entries in this tree. Returns: List with (name, mode, sha) tuples """ return list(self.iteritems()) def _deserialize(self, chunks): """Grab the entries in the tree""" try: parsed_entries = parse_tree(b''.join(chunks)) except ValueError as e: raise ObjectFormatException(e) # TODO: list comprehension is for efficiency in the common (small) # case; if memory efficiency in the large case is a concern, use a # genexp. self._entries = dict([(n, (m, s)) for n, m, s in parsed_entries]) def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way """ super(Tree, self).check() last = None allowed_modes = (stat.S_IFREG | 0o755, stat.S_IFREG | 0o644, stat.S_IFLNK, stat.S_IFDIR, S_IFGITLINK, # TODO: optionally exclude as in git fsck --strict stat.S_IFREG | 0o664) for name, mode, sha in parse_tree(b''.join(self._chunked_text), True): check_hexsha(sha, 'invalid sha %s' % sha) if b'/' in name or name in (b'', b'.', b'..', b'.git'): raise ObjectFormatException( 'invalid name %s' % name.decode('utf-8', 'replace')) if mode not in allowed_modes: raise ObjectFormatException('invalid mode %06o' % mode) entry = (name, (mode, sha)) if last: if key_entry(last) > key_entry(entry): raise ObjectFormatException('entries not sorted') if name == last[0]: raise ObjectFormatException('duplicate entry %s' % name) last = entry def _serialize(self): return list(serialize_tree(self.iteritems())) def as_pretty_string(self): text = [] for name, mode, hexsha in self.iteritems(): text.append(pretty_format_tree_entry(name, mode, hexsha)) return "".join(text) def lookup_path(self, lookup_obj, path): """Look up an object in a Git tree. Args: lookup_obj: Callback for retrieving object by SHA1 path: Path to lookup Returns: A tuple of (mode, SHA) of the resulting path. """ parts = path.split(b'/') sha = self.id mode = None for p in parts: if not p: continue obj = lookup_obj(sha) if not isinstance(obj, Tree): raise NotTreeError(sha) mode, sha = obj[p] return mode, sha def parse_timezone(text): """Parse a timezone text fragment (e.g. '+0100'). Args: text: Text to parse. Returns: Tuple with timezone as seconds difference to UTC and a boolean indicating whether this was a UTC timezone prefixed with a negative sign (-0000). """ # cgit parses the first character as the sign, and the rest # as an integer (using strtol), which could also be negative. # We do the same for compatibility. See #697828. if not text[0] in b'+-': raise ValueError("Timezone must start with + or - (%(text)s)" % vars()) sign = text[:1] offset = int(text[1:]) if sign == b'-': offset = -offset unnecessary_negative_timezone = (offset >= 0 and sign == b'-') signum = (offset < 0) and -1 or 1 offset = abs(offset) hours = int(offset / 100) minutes = (offset % 100) return (signum * (hours * 3600 + minutes * 60), unnecessary_negative_timezone) def format_timezone(offset, unnecessary_negative_timezone=False): """Format a timezone for Git serialization. Args: offset: Timezone offset as seconds difference to UTC unnecessary_negative_timezone: Whether to use a minus sign for UTC or positive timezones (-0000 and --700 rather than +0000 / +0700). """ if offset % 60 != 0: raise ValueError("Unable to handle non-minute offset.") if offset < 0 or unnecessary_negative_timezone: sign = '-' offset = -offset else: sign = '+' return ('%c%02d%02d' % (sign, offset / 3600, (offset / 60) % 60)).encode('ascii') def parse_time_entry(value): """Parse time entry behavior Args: value: Bytes representing a git commit/tag line Raises: ObjectFormatException in case of parsing error (malformed field date) Returns: Tuple of (author, time, (timezone, timezone_neg_utc)) """ try: sep = value.rindex(b'> ') except ValueError: return (value, None, (None, False)) try: person = value[0:sep+1] rest = value[sep+2:] timetext, timezonetext = rest.rsplit(b' ', 1) time = int(timetext) timezone, timezone_neg_utc = parse_timezone(timezonetext) except ValueError as e: raise ObjectFormatException(e) return person, time, (timezone, timezone_neg_utc) def parse_commit(chunks): """Parse a commit object from chunks. Args: chunks: Chunks to parse Returns: Tuple of (tree, parents, author_info, commit_info, encoding, mergetag, gpgsig, message, extra) """ parents = [] extra = [] tree = None author_info = (None, None, (None, None)) commit_info = (None, None, (None, None)) encoding = None mergetag = [] message = None gpgsig = None for field, value in _parse_message(chunks): # TODO(jelmer): Enforce ordering if field == _TREE_HEADER: tree = value elif field == _PARENT_HEADER: parents.append(value) elif field == _AUTHOR_HEADER: author_info = parse_time_entry(value) elif field == _COMMITTER_HEADER: commit_info = parse_time_entry(value) elif field == _ENCODING_HEADER: encoding = value elif field == _MERGETAG_HEADER: mergetag.append(Tag.from_string(value + b'\n')) elif field == _GPGSIG_HEADER: gpgsig = value elif field is None: message = value else: extra.append((field, value)) return (tree, parents, author_info, commit_info, encoding, mergetag, gpgsig, message, extra) class Commit(ShaFile): """A git commit object""" type_name = b'commit' type_num = 1 __slots__ = ('_parents', '_encoding', '_extra', '_author_timezone_neg_utc', '_commit_timezone_neg_utc', '_commit_time', '_author_time', '_author_timezone', '_commit_timezone', '_author', '_committer', '_tree', '_message', '_mergetag', '_gpgsig') def __init__(self): super(Commit, self).__init__() self._parents = [] self._encoding = None self._mergetag = [] self._gpgsig = None self._extra = [] self._author_timezone_neg_utc = False self._commit_timezone_neg_utc = False @classmethod def from_path(cls, path): commit = ShaFile.from_path(path) if not isinstance(commit, cls): raise NotCommitError(path) return commit def _deserialize(self, chunks): (self._tree, self._parents, author_info, commit_info, self._encoding, self._mergetag, self._gpgsig, self._message, self._extra) = ( parse_commit(chunks)) (self._author, self._author_time, (self._author_timezone, self._author_timezone_neg_utc)) = author_info (self._committer, self._commit_time, (self._commit_timezone, self._commit_timezone_neg_utc)) = commit_info def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way """ super(Commit, self).check() self._check_has_member("_tree", "missing tree") self._check_has_member("_author", "missing author") self._check_has_member("_committer", "missing committer") self._check_has_member("_author_time", "missing author time") self._check_has_member("_commit_time", "missing commit time") for parent in self._parents: check_hexsha(parent, "invalid parent sha") check_hexsha(self._tree, "invalid tree sha") check_identity(self._author, "invalid author") check_identity(self._committer, "invalid committer") check_time(self._author_time) check_time(self._commit_time) last = None for field, _ in _parse_message(self._chunked_text): if field == _TREE_HEADER and last is not None: raise ObjectFormatException("unexpected tree") elif field == _PARENT_HEADER and last not in (_PARENT_HEADER, _TREE_HEADER): raise ObjectFormatException("unexpected parent") elif field == _AUTHOR_HEADER and last not in (_TREE_HEADER, _PARENT_HEADER): raise ObjectFormatException("unexpected author") elif field == _COMMITTER_HEADER and last != _AUTHOR_HEADER: raise ObjectFormatException("unexpected committer") elif field == _ENCODING_HEADER and last != _COMMITTER_HEADER: raise ObjectFormatException("unexpected encoding") last = field # TODO: optionally check for duplicate parents def _serialize(self): chunks = [] tree_bytes = ( self._tree.id if isinstance(self._tree, Tree) else self._tree) chunks.append(git_line(_TREE_HEADER, tree_bytes)) for p in self._parents: chunks.append(git_line(_PARENT_HEADER, p)) chunks.append(git_line( _AUTHOR_HEADER, self._author, str(self._author_time).encode('ascii'), format_timezone( self._author_timezone, self._author_timezone_neg_utc))) chunks.append(git_line( _COMMITTER_HEADER, self._committer, str(self._commit_time).encode('ascii'), format_timezone(self._commit_timezone, self._commit_timezone_neg_utc))) if self.encoding: chunks.append(git_line(_ENCODING_HEADER, self.encoding)) for mergetag in self.mergetag: mergetag_chunks = mergetag.as_raw_string().split(b'\n') chunks.append(git_line(_MERGETAG_HEADER, mergetag_chunks[0])) # Embedded extra header needs leading space for chunk in mergetag_chunks[1:]: chunks.append(b' ' + chunk + b'\n') # No trailing empty line if chunks[-1].endswith(b' \n'): chunks[-1] = chunks[-1][:-2] for k, v in self.extra: if b'\n' in k or b'\n' in v: raise AssertionError( "newline in extra data: %r -> %r" % (k, v)) chunks.append(git_line(k, v)) if self.gpgsig: sig_chunks = self.gpgsig.split(b'\n') chunks.append(git_line(_GPGSIG_HEADER, sig_chunks[0])) for chunk in sig_chunks[1:]: chunks.append(git_line(b'', chunk)) chunks.append(b'\n') # There must be a new line after the headers chunks.append(self._message) return chunks tree = serializable_property( "tree", "Tree that is the state of this commit") def _get_parents(self): """Return a list of parents of this commit.""" return self._parents def _set_parents(self, value): """Set a list of parents of this commit.""" self._needs_serialization = True self._parents = value parents = property(_get_parents, _set_parents, doc="Parents of this commit, by their SHA1.") def _get_extra(self): """Return extra settings of this commit.""" return self._extra extra = property( _get_extra, doc="Extra header fields not understood (presumably added in a " "newer version of git). Kept verbatim so the object can " "be correctly reserialized. For private commit metadata, use " "pseudo-headers in Commit.message, rather than this field.") author = serializable_property( "author", "The name of the author of the commit") committer = serializable_property( "committer", "The name of the committer of the commit") message = serializable_property( "message", "The commit message") commit_time = serializable_property( "commit_time", "The timestamp of the commit. As the number of seconds since the " "epoch.") commit_timezone = serializable_property( "commit_timezone", "The zone the commit time is in") author_time = serializable_property( "author_time", "The timestamp the commit was written. As the number of " "seconds since the epoch.") author_timezone = serializable_property( "author_timezone", "Returns the zone the author time is in.") encoding = serializable_property( "encoding", "Encoding of the commit message.") mergetag = serializable_property( "mergetag", "Associated signed tag.") gpgsig = serializable_property( "gpgsig", "GPG Signature.") OBJECT_CLASSES = ( Commit, Tree, Blob, Tag, ) _TYPE_MAP = {} for cls in OBJECT_CLASSES: _TYPE_MAP[cls.type_name] = cls _TYPE_MAP[cls.type_num] = cls # Hold on to the pure-python implementations for testing _parse_tree_py = parse_tree _sorted_tree_items_py = sorted_tree_items try: # Try to import C versions from dulwich._objects import parse_tree, sorted_tree_items except ImportError: pass diff --git a/dulwich/server.py b/dulwich/server.py index 2aae5b6d..29313aff 100644 --- a/dulwich/server.py +++ b/dulwich/server.py @@ -1,1214 +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 -try: - import SocketServer -except ImportError: - import socketserver as SocketServer +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): +class TCPGitRequestHandler(socketserver.StreamRequestHandler): def __init__(self, handlers, *args, **kwargs): self.handlers = handlers - SocketServer.StreamRequestHandler.__init__(self, *args, **kwargs) + 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): +class TCPGitServer(socketserver.TCPServer): allow_reuse_address = True - serve = SocketServer.TCPServer.serve_forever + 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), + 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'\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/compat/test_client.py b/dulwich/tests/compat/test_client.py index cfcd9e48..c1db4ef4 100644 --- a/dulwich/tests/compat/test_client.py +++ b/dulwich/tests/compat/test_client.py @@ -1,609 +1,599 @@ # test_client.py -- Compatibilty tests for git client. # Copyright (C) 2010 Google, Inc. # # 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. # """Compatibilty tests between the Dulwich client and the cgit server.""" import copy from io import BytesIO import os import select import signal import stat import subprocess import sys import tarfile import tempfile import threading import unittest -try: - from urlparse import unquote -except ImportError: - from urllib.parse import unquote +from urllib.parse import unquote - -try: - import BaseHTTPServer - import SimpleHTTPServer -except ImportError: - import http.server - BaseHTTPServer = http.server - SimpleHTTPServer = http.server +import http.server from dulwich import ( client, errors, file, index, protocol, objects, repo, ) from dulwich.tests import ( SkipTest, expectedFailure, ) from dulwich.tests.compat.utils import ( CompatTestCase, check_for_daemon, import_repo_to_dir, rmtree_ro, run_git_or_fail, _DEFAULT_GIT, ) if sys.platform == 'win32': import ctypes class DulwichClientTestBase(object): """Tests for client/server compatibility.""" def setUp(self): self.gitroot = os.path.dirname( import_repo_to_dir('server_new.export').rstrip(os.sep)) self.dest = os.path.join(self.gitroot, 'dest') file.ensure_dir_exists(self.dest) run_git_or_fail(['init', '--quiet', '--bare'], cwd=self.dest) def tearDown(self): rmtree_ro(self.gitroot) def assertDestEqualsSrc(self): repo_dir = os.path.join(self.gitroot, 'server_new.export') dest_repo_dir = os.path.join(self.gitroot, 'dest') with repo.Repo(repo_dir) as src: with repo.Repo(dest_repo_dir) as dest: self.assertReposEqual(src, dest) def _client(self): raise NotImplementedError() def _build_path(self): raise NotImplementedError() def _do_send_pack(self): c = self._client() srcpath = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(srcpath) as src: sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] c.send_pack(self._build_path('/dest'), lambda _: sendrefs, src.generate_pack_data) def test_send_pack(self): self._do_send_pack() self.assertDestEqualsSrc() def test_send_pack_nothing_to_send(self): self._do_send_pack() self.assertDestEqualsSrc() # nothing to send, but shouldn't raise either. self._do_send_pack() @staticmethod def _add_file(repo, tree_id, filename, contents): tree = repo[tree_id] blob = objects.Blob() blob.data = contents.encode('utf-8') repo.object_store.add_object(blob) tree.add(filename.encode('utf-8'), stat.S_IFREG | 0o644, blob.id) repo.object_store.add_object(tree) return tree.id def test_send_pack_from_shallow_clone(self): c = self._client() server_new_path = os.path.join(self.gitroot, 'server_new.export') run_git_or_fail(['config', 'http.uploadpack', 'true'], cwd=server_new_path) run_git_or_fail(['config', 'http.receivepack', 'true'], cwd=server_new_path) remote_path = self._build_path('/server_new.export') with repo.Repo(self.dest) as local: result = c.fetch(remote_path, local, depth=1) for r in result.refs.items(): local.refs.set_if_equals(r[0], None, r[1]) tree_id = local[local.head()].tree for filename, contents in [('bar', 'bar contents'), ('zop', 'zop contents')]: tree_id = self._add_file(local, tree_id, filename, contents) commit_id = local.do_commit( message=b"add " + filename.encode('utf-8'), committer=b"Joe Example ", tree=tree_id) sendrefs = dict(local.get_refs()) del sendrefs[b'HEAD'] c.send_pack(remote_path, lambda _: sendrefs, local.generate_pack_data) with repo.Repo(server_new_path) as remote: self.assertEqual(remote.head(), commit_id) def test_send_without_report_status(self): c = self._client() c._send_capabilities.remove(b'report-status') srcpath = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(srcpath) as src: sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] c.send_pack(self._build_path('/dest'), lambda _: sendrefs, src.generate_pack_data) self.assertDestEqualsSrc() def make_dummy_commit(self, dest): b = objects.Blob.from_string(b'hi') dest.object_store.add_object(b) t = index.commit_tree(dest.object_store, [(b'hi', b.id, 0o100644)]) c = objects.Commit() c.author = c.committer = b'Foo Bar ' c.author_time = c.commit_time = 0 c.author_timezone = c.commit_timezone = 0 c.message = b'hi' c.tree = t dest.object_store.add_object(c) return c.id def disable_ff_and_make_dummy_commit(self): # disable non-fast-forward pushes to the server dest = repo.Repo(os.path.join(self.gitroot, 'dest')) run_git_or_fail(['config', 'receive.denyNonFastForwards', 'true'], cwd=dest.path) commit_id = self.make_dummy_commit(dest) return dest, commit_id def compute_send(self, src): sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] return sendrefs, src.generate_pack_data def test_send_pack_one_error(self): dest, dummy_commit = self.disable_ff_and_make_dummy_commit() dest.refs[b'refs/heads/master'] = dummy_commit repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as src: sendrefs, gen_pack = self.compute_send(src) c = self._client() try: c.send_pack(self._build_path('/dest'), lambda _: sendrefs, gen_pack) except errors.UpdateRefsError as e: self.assertEqual('refs/heads/master failed to update', e.args[0]) self.assertEqual({b'refs/heads/branch': b'ok', b'refs/heads/master': b'non-fast-forward'}, e.ref_status) def test_send_pack_multiple_errors(self): dest, dummy = self.disable_ff_and_make_dummy_commit() # set up for two non-ff errors branch, master = b'refs/heads/branch', b'refs/heads/master' dest.refs[branch] = dest.refs[master] = dummy repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as src: sendrefs, gen_pack = self.compute_send(src) c = self._client() try: c.send_pack(self._build_path('/dest'), lambda _: sendrefs, gen_pack) except errors.UpdateRefsError as e: self.assertIn( str(e), ['{0}, {1} failed to update'.format( branch.decode('ascii'), master.decode('ascii')), '{1}, {0} failed to update'.format( branch.decode('ascii'), master.decode('ascii'))]) self.assertEqual({branch: b'non-fast-forward', master: b'non-fast-forward'}, e.ref_status) def test_archive(self): c = self._client() f = BytesIO() c.archive(self._build_path('/server_new.export'), b'HEAD', f.write) f.seek(0) tf = tarfile.open(fileobj=f) self.assertEqual(['baz', 'foo'], tf.getnames()) def test_fetch_pack(self): c = self._client() with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() def test_fetch_pack_depth(self): c = self._client() with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch(self._build_path('/server_new.export'), dest, depth=1) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertEqual( dest.get_shallow(), set([b'35e0b59e187dd72a0af294aedffc213eaa4d03ff', b'514dc6d3fbfe77361bcaef320c4d21b72bc10be9'])) def test_repeat(self): c = self._client() with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() def test_incremental_fetch_pack(self): self.test_fetch_pack() dest, dummy = self.disable_ff_and_make_dummy_commit() dest.refs[b'refs/heads/master'] = dummy c = self._client() repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as dest: result = c.fetch(self._build_path('/dest'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() def test_fetch_pack_no_side_band_64k(self): c = self._client() c._fetch_capabilities.remove(b'side-band-64k') with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() def test_fetch_pack_zero_sha(self): # zero sha1s are already present on the client, and should # be ignored c = self._client() with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch( self._build_path('/server_new.export'), dest, lambda refs: [protocol.ZERO_SHA]) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) def test_send_remove_branch(self): with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: dummy_commit = self.make_dummy_commit(dest) dest.refs[b'refs/heads/master'] = dummy_commit dest.refs[b'refs/heads/abranch'] = dummy_commit sendrefs = dict(dest.refs) sendrefs[b'refs/heads/abranch'] = b"00" * 20 del sendrefs[b'HEAD'] def gen_pack(have, want, ofs_delta=False): return 0, [] c = self._client() self.assertEqual(dest.refs[b"refs/heads/abranch"], dummy_commit) c.send_pack( self._build_path('/dest'), lambda _: sendrefs, gen_pack) self.assertFalse(b"refs/heads/abranch" in dest.refs) def test_get_refs(self): c = self._client() refs = c.get_refs(self._build_path('/server_new.export')) repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as dest: self.assertDictEqual(dest.refs.as_dict(), refs) class DulwichTCPClientTest(CompatTestCase, DulwichClientTestBase): def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) if check_for_daemon(limit=1): raise SkipTest('git-daemon was already running on port %s' % protocol.TCP_GIT_PORT) fd, self.pidfile = tempfile.mkstemp(prefix='dulwich-test-git-client', suffix=".pid") os.fdopen(fd).close() args = [_DEFAULT_GIT, 'daemon', '--verbose', '--export-all', '--pid-file=%s' % self.pidfile, '--base-path=%s' % self.gitroot, '--enable=receive-pack', '--enable=upload-archive', '--listen=localhost', '--reuseaddr', self.gitroot] self.process = subprocess.Popen( args, cwd=self.gitroot, stdout=subprocess.PIPE, stderr=subprocess.PIPE) if not check_for_daemon(): raise SkipTest('git-daemon failed to start') def tearDown(self): with open(self.pidfile) as f: pid = int(f.read().strip()) if sys.platform == 'win32': PROCESS_TERMINATE = 1 handle = ctypes.windll.kernel32.OpenProcess( PROCESS_TERMINATE, False, pid) ctypes.windll.kernel32.TerminateProcess(handle, -1) ctypes.windll.kernel32.CloseHandle(handle) else: try: os.kill(pid, signal.SIGKILL) os.unlink(self.pidfile) except (OSError, IOError): pass self.process.wait() self.process.stdout.close() self.process.stderr.close() DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) def _client(self): return client.TCPGitClient('localhost') def _build_path(self, path): return path if sys.platform == 'win32': @expectedFailure def test_fetch_pack_no_side_band_64k(self): DulwichClientTestBase.test_fetch_pack_no_side_band_64k(self) class TestSSHVendor(object): @staticmethod def run_command(host, command, username=None, port=None, password=None, key_filename=None): cmd, path = command.split(' ') cmd = cmd.split('-', 1) path = path.replace("'", "") p = subprocess.Popen(cmd + [path], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return client.SubprocessWrapper(p) class DulwichMockSSHClientTest(CompatTestCase, DulwichClientTestBase): def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) self.real_vendor = client.get_ssh_vendor client.get_ssh_vendor = TestSSHVendor def tearDown(self): DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) client.get_ssh_vendor = self.real_vendor def _client(self): return client.SSHGitClient('localhost') def _build_path(self, path): return self.gitroot + path class DulwichSubprocessClientTest(CompatTestCase, DulwichClientTestBase): def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) def tearDown(self): DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) def _client(self): return client.SubprocessGitClient() def _build_path(self, path): return self.gitroot + path -class GitHTTPRequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler): +class GitHTTPRequestHandler(http.server.SimpleHTTPRequestHandler): """HTTP Request handler that calls out to 'git http-backend'.""" # Make rfile unbuffered -- we need to read one line and then pass # the rest to a subprocess, so we can't use buffered input. rbufsize = 0 def do_POST(self): self.run_backend() def do_GET(self): self.run_backend() def send_head(self): return self.run_backend() def log_request(self, code='-', size='-'): # Let's be quiet, the test suite is noisy enough already pass def run_backend(self): """Call out to git http-backend.""" # Based on CGIHTTPServer.CGIHTTPRequestHandler.run_cgi: # Copyright (c) 2001-2010 Python Software Foundation; # All Rights Reserved # Licensed under the Python Software Foundation License. rest = self.path # find an explicit query string, if present. i = rest.rfind('?') if i >= 0: rest, query = rest[:i], rest[i+1:] else: query = '' env = copy.deepcopy(os.environ) env['SERVER_SOFTWARE'] = self.version_string() env['SERVER_NAME'] = self.server.server_name env['GATEWAY_INTERFACE'] = 'CGI/1.1' env['SERVER_PROTOCOL'] = self.protocol_version env['SERVER_PORT'] = str(self.server.server_port) env['GIT_PROJECT_ROOT'] = self.server.root_path env["GIT_HTTP_EXPORT_ALL"] = "1" env['REQUEST_METHOD'] = self.command uqrest = unquote(rest) env['PATH_INFO'] = uqrest env['SCRIPT_NAME'] = "/" if query: env['QUERY_STRING'] = query host = self.address_string() if host != self.client_address[0]: env['REMOTE_HOST'] = host env['REMOTE_ADDR'] = self.client_address[0] authorization = self.headers.get("authorization") if authorization: authorization = authorization.split() if len(authorization) == 2: import base64 import binascii env['AUTH_TYPE'] = authorization[0] if authorization[0].lower() == "basic": try: authorization = base64.decodestring(authorization[1]) except binascii.Error: pass else: authorization = authorization.split(':') if len(authorization) == 2: env['REMOTE_USER'] = authorization[0] # XXX REMOTE_IDENT content_type = self.headers.get('content-type') if content_type: env['CONTENT_TYPE'] = content_type length = self.headers.get('content-length') if length: env['CONTENT_LENGTH'] = length referer = self.headers.get('referer') if referer: env['HTTP_REFERER'] = referer accept = [] for line in self.headers.getallmatchingheaders('accept'): if line[:1] in "\t\n\r ": accept.append(line.strip()) else: accept = accept + line[7:].split(',') env['HTTP_ACCEPT'] = ','.join(accept) ua = self.headers.get('user-agent') if ua: env['HTTP_USER_AGENT'] = ua co = self.headers.get('cookie') if co: env['HTTP_COOKIE'] = co # XXX Other HTTP_* headers # Since we're setting the env in the parent, provide empty # values to override previously set values for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH', 'HTTP_USER_AGENT', 'HTTP_COOKIE', 'HTTP_REFERER'): env.setdefault(k, "") self.wfile.write(b"HTTP/1.1 200 Script output follows\r\n") self.wfile.write( ("Server: %s\r\n" % self.server.server_name).encode('ascii')) self.wfile.write( ("Date: %s\r\n" % self.date_time_string()).encode('ascii')) decoded_query = query.replace('+', ' ') try: nbytes = int(length) except (TypeError, ValueError): nbytes = 0 if self.command.lower() == "post" and nbytes > 0: data = self.rfile.read(nbytes) else: data = None env['CONTENT_LENGTH'] = '0' # throw away additional data [see bug #427345] while select.select([self.rfile._sock], [], [], 0)[0]: if not self.rfile._sock.recv(1): break args = ['http-backend'] if '=' not in decoded_query: args.append(decoded_query) stdout = run_git_or_fail( args, input=data, env=env, stderr=subprocess.PIPE) self.wfile.write(stdout) -class HTTPGitServer(BaseHTTPServer.HTTPServer): +class HTTPGitServer(http.server.HTTPServer): allow_reuse_address = True def __init__(self, server_address, root_path): - BaseHTTPServer.HTTPServer.__init__( + http.server.HTTPServer.__init__( self, server_address, GitHTTPRequestHandler) self.root_path = root_path self.server_name = "localhost" def get_url(self): return 'http://%s:%s/' % (self.server_name, self.server_port) class DulwichHttpClientTest(CompatTestCase, DulwichClientTestBase): min_git_version = (1, 7, 0, 2) def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) self._httpd = HTTPGitServer(("localhost", 0), self.gitroot) self.addCleanup(self._httpd.shutdown) threading.Thread(target=self._httpd.serve_forever).start() run_git_or_fail(['config', 'http.uploadpack', 'true'], cwd=self.dest) run_git_or_fail(['config', 'http.receivepack', 'true'], cwd=self.dest) def tearDown(self): DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) self._httpd.shutdown() self._httpd.socket.close() def _client(self): return client.HttpGitClient(self._httpd.get_url()) def _build_path(self, path): return path def test_archive(self): raise SkipTest("exporting archives not supported over http") diff --git a/dulwich/tests/test_client.py b/dulwich/tests/test_client.py index d8a6c6a8..9f003480 100644 --- a/dulwich/tests/test_client.py +++ b/dulwich/tests/test_client.py @@ -1,1359 +1,1353 @@ # test_client.py -- Tests for the git protocol, client side # Copyright (C) 2009 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # from io import BytesIO import base64 import os import sys import shutil import tempfile import warnings -try: - from urllib import quote as urlquote -except ImportError: - from urllib.parse import quote as urlquote - -try: - import urlparse -except ImportError: - import urllib.parse as urlparse +from urllib.parse import ( + quote as urlquote, + urlparse, + ) import urllib3 import dulwich from dulwich import ( client, ) from dulwich.client import ( InvalidWants, LocalGitClient, TraditionalGitClient, TCPGitClient, SSHGitClient, HttpGitClient, FetchPackResult, ReportStatusParser, SendPackError, StrangeHostname, SubprocessSSHVendor, PLinkSSHVendor, UpdateRefsError, check_wants, default_urllib3_manager, get_credentials_from_store, get_transport_and_path, get_transport_and_path_from_url, parse_rsync_url, ) from dulwich.config import ( ConfigDict, ) from dulwich.tests import ( TestCase, ) from dulwich.protocol import ( TCP_GIT_PORT, Protocol, ) from dulwich.pack import ( pack_objects_to_data, write_pack_data, write_pack_objects, ) from dulwich.objects import ( Commit, Tree ) from dulwich.repo import ( MemoryRepo, Repo, ) from dulwich.tests import skipIf from dulwich.tests.utils import ( open_repo, tear_down_repo, setup_warning_catcher, ) class DummyClient(TraditionalGitClient): def __init__(self, can_read, read, write): self.can_read = can_read self.read = read self.write = write TraditionalGitClient.__init__(self) def _connect(self, service, path): return Protocol(self.read, self.write), self.can_read, None class DummyPopen(): def __init__(self, *args, **kwards): self.stdin = BytesIO(b"stdin") self.stdout = BytesIO(b"stdout") self.stderr = BytesIO(b"stderr") self.returncode = 0 self.args = args self.kwargs = kwards def communicate(self, *args, **kwards): return ('Running', '') def wait(self, *args, **kwards): return False # TODO(durin42): add unit-level tests of GitClient class GitClientTests(TestCase): def setUp(self): super(GitClientTests, self).setUp() self.rout = BytesIO() self.rin = BytesIO() self.client = DummyClient(lambda x: True, self.rin.read, self.rout.write) def test_caps(self): agent_cap = ( 'agent=dulwich/%d.%d.%d' % dulwich.__version__).encode('ascii') self.assertEqual(set([b'multi_ack', b'side-band-64k', b'ofs-delta', b'thin-pack', b'multi_ack_detailed', b'shallow', agent_cap]), set(self.client._fetch_capabilities)) self.assertEqual( set([b'delete-refs', b'ofs-delta', b'report-status', b'side-band-64k', agent_cap]), set(self.client._send_capabilities)) def test_archive_ack(self): self.rin.write( b'0009NACK\n' b'0000') self.rin.seek(0) self.client.archive(b'bla', b'HEAD', None, None) self.assertEqual(self.rout.getvalue(), b'0011argument HEAD0000') def test_fetch_empty(self): self.rin.write(b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual(heads, {}) return [] ret = self.client.fetch_pack(b'/', check_heads, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) def test_fetch_pack_ignores_magic_ref(self): self.rin.write( b'00000000000000000000000000000000000000000000 capabilities^{}' b'\x00 multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual({}, heads) return [] ret = self.client.fetch_pack(b'bla', check_heads, None, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') def test_fetch_pack_none(self): self.rin.write( b'008855dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 HEAD\x00multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) ret = self.client.fetch_pack( b'bla', lambda heads: [], None, None, None) self.assertEqual( {b'HEAD': b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7'}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') def test_send_pack_no_sideband64k_with_update_ref_error(self): # No side-bank-64k reported by server shouldn't try to parse # side band data pkts = [b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 capabilities^{}' b'\x00 report-status delete-refs ofs-delta\n', b'', b"unpack ok", b"ng refs/foo/bar pre-receive hook declined", b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' def update_refs(refs): return {b'refs/foo/bar': commit.id, } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, ''), ]) self.assertRaises(UpdateRefsError, self.client.send_pack, "blah", update_refs, generate_pack_data) def test_send_pack_none(self): self.rin.write( b'0078310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ' b'side-band-64k quiet ofs-delta\n' b'0000') self.rin.seek(0) def update_refs(refs): return { b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, set(), generate_pack_data) self.assertEqual(self.rout.getvalue(), b'0000') def test_send_pack_keep_and_delete(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'003f310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/keepme\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00delete-refs ofs-delta report-status0000') def test_send_pack_delete_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00delete-refs ofs-delta report-status0000') def test_send_pack_new_ref_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) def update_refs(refs): return { b'refs/heads/blah12': b'310ca9477129b8586fa2afc779c1f57cf64bba6c', b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] f = BytesIO() write_pack_objects(f, {}) self.client.send_pack('/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b0000000000000000000000000000000000000000 ' b'310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/blah12\x00delete-refs ofs-delta report-status0000' + f.getvalue()) def test_send_pack_new_ref(self): self.rin.write( b'0064310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' def update_refs(refs): return { b'refs/heads/blah12': commit.id, b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, b''), ]) f = BytesIO() write_pack_data(f, *generate_pack_data(None, None)) self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b0000000000000000000000000000000000000000 ' + commit.id + b' refs/heads/blah12\x00delete-refs ofs-delta report-status0000' + f.getvalue()) def test_send_pack_no_deleteref_delete_only(self): pkts = [b'310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/master' b'\x00 report-status ofs-delta\n', b'', b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.assertRaises(UpdateRefsError, self.client.send_pack, b"/", update_refs, generate_pack_data) self.assertEqual(self.rout.getvalue(), b'0000') class TestGetTransportAndPath(TestCase): def test_tcp(self): c, path = get_transport_and_path('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_git_ssh_explicit(self): c, path = get_transport_and_path('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path('ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_username_and_port_explicit_unknown_scheme(self): c, path = get_transport_and_path( 'unknown://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('unknown', c.host) self.assertEqual('//git@server:7999/dply/stuff.git', path) def test_username_and_port_explicit(self): c, path = get_transport_and_path( 'ssh://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('git', c.username) self.assertEqual('server', c.host) self.assertEqual(7999, c.port) self.assertEqual('/dply/stuff.git', path) def test_ssh_abspath_doubleslash(self): c, path = get_transport_and_path('git+ssh://foo.com//bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('//bar/baz', path) def test_ssh_port(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_implicit(self): c, path = get_transport_and_path('foo:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_host(self): c, path = get_transport_and_path('foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_user_host(self): c, path = get_transport_and_path('user@foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('/bar/baz', path) def test_ssh_relpath(self): c, path = get_transport_and_path('foo:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_host_relpath(self): c, path = get_transport_and_path('foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_user_host_relpath(self): c, path = get_transport_and_path('user@foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('bar/baz', path) def test_local(self): c, path = get_transport_and_path('foo.bar/baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('foo.bar/baz', path) @skipIf(sys.platform != 'win32', 'Behaviour only happens on windows.') def test_local_abs_windows_path(self): c, path = get_transport_and_path('C:\\foo.bar\\baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('C:\\foo.bar\\baz', path) def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 c, path = get_transport_and_path('prospero://bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_http_auth(self): url = 'https://user:passwd@github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) def test_http_auth_with_username(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path( url, username='user2', password='blah') self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user2', c._username) self.assertEqual('blah', c._password) def test_http_auth_with_username_and_in_url(self): url = 'https://user:passwd@github.com/jelmer/dulwich' c, path = get_transport_and_path( url, username='user2', password='blah') self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) def test_http_no_auth(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertIs(None, c._username) self.assertIs(None, c._password) class TestGetTransportAndPathFromUrl(TestCase): def test_tcp(self): c, path = get_transport_and_path_from_url('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path_from_url('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path_from_url('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/~/bar/baz', path) def test_ssh_port_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/~/bar/baz', path) def test_ssh_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.com:bar/baz') def test_ssh_user_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'user@foo.com:bar/baz') def test_local_path(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.bar/baz') def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 self.assertRaises( ValueError, get_transport_and_path_from_url, 'prospero://bar/baz') def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path_from_url(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('https://github.com', c.get_url(b'/')) self.assertEqual('/jelmer/dulwich', path) def test_http_port(self): url = 'https://github.com:9090/jelmer/dulwich' c, path = get_transport_and_path_from_url(url) self.assertEqual('https://github.com:9090', c.get_url(b'/')) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_file(self): c, path = get_transport_and_path_from_url('file:///home/jelmer/foo') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('/home/jelmer/foo', path) class TestSSHVendor(object): def __init__(self): self.host = None self.command = "" self.username = None self.port = None self.password = None self.key_filename = None def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): self.host = host self.command = command self.username = username self.port = port self.password = password self.key_filename = key_filename class Subprocess: pass setattr(Subprocess, 'read', lambda: None) setattr(Subprocess, 'write', lambda: None) setattr(Subprocess, 'close', lambda: None) setattr(Subprocess, 'can_read', lambda: None) return Subprocess() class SSHGitClientTests(TestCase): def setUp(self): super(SSHGitClientTests, self).setUp() self.server = TestSSHVendor() self.real_vendor = client.get_ssh_vendor client.get_ssh_vendor = lambda: self.server self.client = SSHGitClient('git.samba.org') def tearDown(self): super(SSHGitClientTests, self).tearDown() client.get_ssh_vendor = self.real_vendor def test_get_url(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org') url = c.get_url(path) self.assertEqual('ssh://git.samba.org/tmp/repo.git', url) def test_get_url_with_username_and_port(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org', port=2222, username='user') url = c.get_url(path) self.assertEqual('ssh://user@git.samba.org:2222/tmp/repo.git', url) def test_default_command(self): self.assertEqual( b'git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack') self.assertEqual( b'/usr/lib/git/git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path_spaces(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack -ibla') self.assertEqual(b"/usr/lib/git/git-upload-pack -ibla", self.client._get_cmd_path(b'upload-pack')) def test_connect(self): server = self.server client = self.client client.username = b"username" client.port = 1337 client._connect(b"command", b"/path/to/repo") self.assertEqual(b"username", server.username) self.assertEqual(1337, server.port) self.assertEqual("git-command '/path/to/repo'", server.command) client._connect(b"relative-command", b"/~/path/to/repo") self.assertEqual("git-relative-command '~/path/to/repo'", server.command) class ReportStatusParserTests(TestCase): def test_invalid_pack(self): parser = ReportStatusParser() parser.handle_packet(b"unpack error - foo bar") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) self.assertRaises(SendPackError, parser.check) def test_update_refs_error(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ng refs/foo/bar need to pull") parser.handle_packet(None) self.assertRaises(UpdateRefsError, parser.check) def test_ok(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) parser.check() class LocalGitClientTests(TestCase): def test_get_url(self): path = "/tmp/repo.git" c = LocalGitClient() url = c.get_url(path) self.assertEqual('file:///tmp/repo.git', url) def test_fetch_into_empty(self): c = LocalGitClient() t = MemoryRepo() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) self.assertEqual(s.get_refs(), c.fetch(s.path, t).refs) def test_fetch_empty(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = {} ret = c.fetch_pack( s.path, lambda heads: [], graph_walker=walker, pack_data=out.write) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) self.assertEqual( {b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual( b"PACK\x00\x00\x00\x02\x00\x00\x00\x00\x02\x9d\x08" b"\x82;\xd8\xa8\xea\xb5\x10\xadj\xc7\\\x82<\xfd>\xd3\x1e", out.getvalue()) def test_fetch_pack_none(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = MemoryRepo().get_graph_walker() ret = c.fetch_pack( s.path, lambda heads: [b"a90fa2d900a17e99b433217e988c4eb4a2e9a097"], graph_walker=walker, pack_data=out.write) self.assertEqual({b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) # Hardcoding is not ideal, but we'll fix that some other day.. self.assertTrue(out.getvalue().startswith( b'PACK\x00\x00\x00\x02\x00\x00\x00\x07')) def test_send_pack_without_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target = open_repo('a.git') self.addCleanup(tear_down_repo, target) self.send_and_verify(b"master", local, target) def test_send_pack_with_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) with Repo.init_bare(target_path) as target: self.send_and_verify(b"master", local, target) def test_get_refs(self): local = open_repo('refs.git') self.addCleanup(tear_down_repo, local) client = LocalGitClient() refs = client.get_refs(local.path) self.assertDictEqual(local.refs.as_dict(), refs) def send_and_verify(self, branch, local, target): """Send branch from local to remote repository and verify it worked.""" client = LocalGitClient() ref_name = b"refs/heads/" + branch new_refs = client.send_pack(target.path, lambda _: {ref_name: local.refs[ref_name]}, local.generate_pack_data) self.assertEqual(local.refs[ref_name], new_refs[ref_name]) obj_local = local.get_object(new_refs[ref_name]) obj_target = target.get_object(new_refs[ref_name]) self.assertEqual(obj_local, obj_target) class HttpGitClientTests(TestCase): @staticmethod def b64encode(s): """Python 2/3 compatible Base64 encoder. Returns string.""" try: return base64.b64encode(s) except TypeError: return base64.b64encode(s.encode('latin1')).decode('ascii') def test_get_url(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_bytes_path(self): base_url = 'https://github.com/jelmer/dulwich' path_bytes = b'/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path_bytes) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_with_username_and_passwd(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url, username='USERNAME', password='PASSWD') url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_init_username_passwd_set(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None, username='user', password='passwd') self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % ('user', 'passwd') b64_credentials = self.b64encode(auth_string) expected_basic_auth = 'Basic %s' % b64_credentials self.assertEqual(basic_auth, expected_basic_auth) def test_init_no_username_passwd(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None) self.assertIs(None, c._username) self.assertIs(None, c._password) self.assertNotIn('authorization', c.pool_manager.headers) def test_from_parsedurl_on_url_with_quoted_credentials(self): original_username = 'john|the|first' quoted_username = urlquote(original_username) original_password = 'Ya#1$2%3' quoted_password = urlquote(original_password) url = 'https://{username}:{password}@github.com/jelmer/dulwich'.format( username=quoted_username, password=quoted_password ) - c = HttpGitClient.from_parsedurl(urlparse.urlparse(url)) + c = HttpGitClient.from_parsedurl(urlparse(url)) self.assertEqual(original_username, c._username) self.assertEqual(original_password, c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % (original_username, original_password) b64_credentials = self.b64encode(auth_string) expected_basic_auth = 'Basic %s' % str(b64_credentials) self.assertEqual(basic_auth, expected_basic_auth) def test_url_redirect_location(self): - from urllib3.response import HTTPResponse test_data = { 'https://gitlab.com/inkscape/inkscape/': { 'redirect_url': 'https://gitlab.com/inkscape/inkscape.git/', 'refs_data': (b'001e# service=git-upload-pack\n00000032' b'fb2bebf4919a011f0fd7cec085443d0031228e76 ' b'HEAD\n0000') }, 'https://github.com/jelmer/dulwich/': { 'redirect_url': 'https://github.com/jelmer/dulwich/', 'refs_data': (b'001e# service=git-upload-pack\n00000032' b'3ff25e09724aa4d86ea5bca7d5dd0399a3c8bfcf ' b'HEAD\n0000') } } tail = 'info/refs?service=git-upload-pack' # we need to mock urllib3.PoolManager as this test will fail # otherwise without an active internet connection class PoolManagerMock(): def __init__(self): self.headers = {} def request(self, method, url, fields=None, headers=None, redirect=True): base_url = url[:-len(tail)] redirect_base_url = test_data[base_url]['redirect_url'] redirect_url = redirect_base_url + tail headers = { 'Content-Type': 'application/x-git-upload-pack-advertisement' } body = test_data[base_url]['refs_data'] # urllib3 handles automatic redirection by default status = 200 request_url = redirect_url # simulate urllib3 behavior when redirect parameter is False if redirect is False: request_url = url if redirect_base_url != base_url: body = '' headers['location'] = redirect_url status = 301 return HTTPResponse(body=body, headers=headers, request_method=method, request_url=request_url, status=status) pool_manager = PoolManagerMock() for base_url in test_data.keys(): # instantiate HttpGitClient with mocked pool manager c = HttpGitClient(base_url, pool_manager=pool_manager, config=None) # call method that detects url redirection _, _, processed_url = c._discover_references(b'git-upload-pack', base_url) # send the same request as the method above without redirection resp = c.pool_manager.request('GET', base_url + tail, redirect=False) # check expected behavior of urllib3 redirect_location = resp.get_redirect_location() if resp.status == 200: self.assertFalse(redirect_location) if redirect_location: # check that url redirection has been correctly detected self.assertEqual(processed_url, redirect_location[:-len(tail)]) else: # check also the no redirection case self.assertEqual(processed_url, base_url) class TCPGitClientTests(TestCase): def test_get_url(self): host = 'github.com' path = '/jelmer/dulwich' c = TCPGitClient(host) url = c.get_url(path) self.assertEqual('git://github.com/jelmer/dulwich', url) def test_get_url_with_port(self): host = 'github.com' path = '/jelmer/dulwich' port = 9090 c = TCPGitClient(host, port=port) url = c.get_url(path) self.assertEqual('git://github.com:9090/jelmer/dulwich', url) class DefaultUrllib3ManagerTest(TestCase): def test_no_config(self): manager = default_urllib3_manager(config=None) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_proxy(self): manager = default_urllib3_manager(config=ConfigDict()) self.assertNotIsInstance(manager, urllib3.ProxyManager) self.assertIsInstance(manager, urllib3.PoolManager) def test_config_no_proxy_custom_cls(self): class CustomPoolManager(urllib3.PoolManager): pass manager = default_urllib3_manager(config=ConfigDict(), pool_manager_cls=CustomPoolManager) self.assertIsInstance(manager, CustomPoolManager) def test_config_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'true') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'false') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') def test_config_proxy(self): config = ConfigDict() config.set(b'http', b'proxy', b'http://localhost:3128/') manager = default_urllib3_manager(config=config) self.assertIsInstance(manager, urllib3.ProxyManager) self.assertTrue(hasattr(manager, 'proxy')) self.assertEqual(manager.proxy.scheme, 'http') self.assertEqual(manager.proxy.host, 'localhost') self.assertEqual(manager.proxy.port, 3128) def test_config_proxy_custom_cls(self): class CustomProxyManager(urllib3.ProxyManager): pass config = ConfigDict() config.set(b'http', b'proxy', b'http://localhost:3128/') manager = default_urllib3_manager(config=config, proxy_manager_cls=CustomProxyManager) self.assertIsInstance(manager, CustomProxyManager) def test_config_no_verify_ssl(self): manager = default_urllib3_manager(config=None, cert_reqs="CERT_NONE") self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') class SubprocessSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = SubprocessSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345') def test_run_command_password_and_privkey(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') def test_run_command_with_port_username_and_privkey(self): expected = ['ssh', '-x', '-p', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = SubprocessSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class PLinkSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = PLinkSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password_and_privkey(self): vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command( 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-pw', '12345', '-i', '/tmp/id_rsa', 'host', 'git-clone-url'] self.assertListEqual(expected, args[0]) def test_run_command_password(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + ['-pw', '12345', 'host', 'git-clone-url'] vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command('host', 'git-clone-url', password='12345') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args self.assertListEqual(expected, args[0]) def test_run_command_with_port_username_and_privkey(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-P', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = PLinkSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class RsyncUrlTests(TestCase): def test_simple(self): self.assertEqual( parse_rsync_url('foo:bar/path'), (None, 'foo', 'bar/path')) self.assertEqual( parse_rsync_url('user@foo:bar/path'), ('user', 'foo', 'bar/path')) def test_path(self): self.assertRaises(ValueError, parse_rsync_url, '/path') class CheckWantsTests(TestCase): def test_fine(self): check_wants( [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) def test_missing(self): self.assertRaises( InvalidWants, check_wants, [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) def test_annotated(self): self.assertRaises( InvalidWants, check_wants, [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262', b'refs/heads/blah^{}': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) class FetchPackResultTests(TestCase): def test_eq(self): self.assertEqual( FetchPackResult( {b'refs/heads/master': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}, {}, b'user/agent'), FetchPackResult( {b'refs/heads/master': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}, {}, b'user/agent')) class GitCredentialStoreTests(TestCase): @classmethod def setUpClass(cls): with tempfile.NamedTemporaryFile(delete=False) as f: f.write(b'https://user:pass@example.org') cls.fname = f.name @classmethod def tearDownClass(cls): os.unlink(cls.fname) def test_nonmatching_scheme(self): self.assertEqual( get_credentials_from_store( b'http', b'example.org', fnames=[self.fname]), None) def test_nonmatching_hostname(self): self.assertEqual( get_credentials_from_store( b'https', b'noentry.org', fnames=[self.fname]), None) def test_match_without_username(self): self.assertEqual( get_credentials_from_store( b'https', b'example.org', fnames=[self.fname]), (b'user', b'pass')) def test_match_with_matching_username(self): self.assertEqual( get_credentials_from_store( b'https', b'example.org', b'user', fnames=[self.fname]), (b'user', b'pass')) def test_no_match_with_nonmatching_username(self): self.assertEqual( get_credentials_from_store( b'https', b'example.org', b'otheruser', fnames=[self.fname]), None) diff --git a/dulwich/tests/test_porcelain.py b/dulwich/tests/test_porcelain.py index bd15d933..cc65ece2 100644 --- a/dulwich/tests/test_porcelain.py +++ b/dulwich/tests/test_porcelain.py @@ -1,1841 +1,1837 @@ # test_porcelain.py -- porcelain tests # 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.porcelain.""" -from io import BytesIO -try: - from StringIO import StringIO -except ImportError: - from io import StringIO +from io import BytesIO, StringIO import errno import os import shutil import tarfile import tempfile import time from dulwich import porcelain from dulwich.diff_tree import tree_changes from dulwich.objects import ( Blob, Tag, Tree, ZERO_SHA, ) from dulwich.repo import ( NoIndexPresent, Repo, ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( build_commit_graph, make_commit, make_object, ) def flat_walk_dir(dir_to_walk): for dirpath, _, filenames in os.walk(dir_to_walk): rel_dirpath = os.path.relpath(dirpath, dir_to_walk) if not dirpath == dir_to_walk: yield rel_dirpath for filename in filenames: if dirpath == dir_to_walk: yield filename else: yield os.path.join(rel_dirpath, filename) class PorcelainTestCase(TestCase): def setUp(self): super(PorcelainTestCase, self).setUp() self.test_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.test_dir) self.repo_path = os.path.join(self.test_dir, 'repo') self.repo = Repo.init(self.repo_path, mkdir=True) self.addCleanup(self.repo.close) class ArchiveTests(PorcelainTestCase): """Tests for the archive command.""" def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/master"] = c3.id out = BytesIO() err = BytesIO() porcelain.archive(self.repo.path, b"refs/heads/master", outstream=out, errstream=err) self.assertEqual(b"", err.getvalue()) tf = tarfile.TarFile(fileobj=out) self.addCleanup(tf.close) self.assertEqual([], tf.getnames()) class UpdateServerInfoTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/foo"] = c3.id porcelain.update_server_info(self.repo.path) self.assertTrue(os.path.exists( os.path.join(self.repo.controldir(), 'info', 'refs'))) class CommitTests(PorcelainTestCase): def test_custom_author(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/foo"] = c3.id sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) def test_unicode(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/foo"] = c3.id sha = porcelain.commit( self.repo.path, message="Some message", author="Joe ", committer="Bob ") self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) class CleanTests(PorcelainTestCase): def put_files(self, tracked, ignored, untracked, empty_dirs): """Put the described files in the wd """ all_files = tracked | ignored | untracked for file_path in all_files: abs_path = os.path.join(self.repo.path, file_path) # File may need to be written in a dir that doesn't exist yet, so # create the parent dir(s) as necessary parent_dir = os.path.dirname(abs_path) try: os.makedirs(parent_dir) except OSError as err: if not err.errno == errno.EEXIST: raise err with open(abs_path, 'w') as f: f.write('') with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.writelines(ignored) for dir_path in empty_dirs: os.mkdir(os.path.join(self.repo.path, 'empty_dir')) files_to_add = [os.path.join(self.repo.path, t) for t in tracked] porcelain.add(repo=self.repo.path, paths=files_to_add) porcelain.commit(repo=self.repo.path, message="init commit") def assert_wd(self, expected_paths): """Assert paths of files and dirs in wd are same as expected_paths """ control_dir_rel = os.path.relpath( self.repo._controldir, self.repo.path) # normalize paths to simplify comparison across platforms found_paths = { os.path.normpath(p) for p in flat_walk_dir(self.repo.path) if not p.split(os.sep)[0] == control_dir_rel} norm_expected_paths = {os.path.normpath(p) for p in expected_paths} self.assertEqual(found_paths, norm_expected_paths) def test_from_root(self): self.put_files( tracked={ 'tracked_file', 'tracked_dir/tracked_file', '.gitignore'}, ignored={ 'ignored_file'}, untracked={ 'untracked_file', 'tracked_dir/untracked_dir/untracked_file', 'untracked_dir/untracked_dir/untracked_file'}, empty_dirs={ 'empty_dir'}) porcelain.clean(repo=self.repo.path, target_dir=self.repo.path) self.assert_wd({ 'tracked_file', 'tracked_dir/tracked_file', '.gitignore', 'ignored_file', 'tracked_dir'}) def test_from_subdir(self): self.put_files( tracked={ 'tracked_file', 'tracked_dir/tracked_file', '.gitignore'}, ignored={ 'ignored_file'}, untracked={ 'untracked_file', 'tracked_dir/untracked_dir/untracked_file', 'untracked_dir/untracked_dir/untracked_file'}, empty_dirs={ 'empty_dir'}) porcelain.clean( repo=self.repo, target_dir=os.path.join(self.repo.path, 'untracked_dir')) self.assert_wd({ 'tracked_file', 'tracked_dir/tracked_file', '.gitignore', 'ignored_file', 'untracked_file', 'tracked_dir/untracked_dir/untracked_file', 'empty_dir', 'untracked_dir', 'tracked_dir', 'tracked_dir/untracked_dir'}) class CloneTests(PorcelainTestCase): def test_simple_local(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1], [2, 1], [3, 1, 2]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)], 2: [(b'f1', f1_1), (b'f2', f1_1)], 3: [(b'f1', f1_1), (b'f2', f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id self.repo.refs[b"refs/tags/foo"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) r = porcelain.clone(self.repo.path, target_path, checkout=False, errstream=errstream) self.addCleanup(r.close) self.assertEqual(r.path, target_path) target_repo = Repo(target_path) self.assertEqual(0, len(target_repo.open_index())) self.assertEqual(c3.id, target_repo.refs[b'refs/tags/foo']) self.assertTrue(b'f1' not in os.listdir(target_path)) self.assertTrue(b'f2' not in os.listdir(target_path)) c = r.get_config() encoded_path = self.repo.path if not isinstance(encoded_path, bytes): encoded_path = encoded_path.encode('utf-8') 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_simple_local_with_checkout(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1], [2, 1], [3, 1, 2]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)], 2: [(b'f1', f1_1), (b'f2', f1_1)], 3: [(b'f1', f1_1), (b'f2', f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) with porcelain.clone(self.repo.path, target_path, checkout=True, errstream=errstream) as r: self.assertEqual(r.path, target_path) with Repo(target_path) as r: self.assertEqual(r.head(), c3.id) self.assertTrue('f1' in os.listdir(target_path)) self.assertTrue('f2' in os.listdir(target_path)) def test_bare_local_with_checkout(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1], [2, 1], [3, 1, 2]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)], 2: [(b'f1', f1_1), (b'f2', f1_1)], 3: [(b'f1', f1_1), (b'f2', f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) with porcelain.clone( self.repo.path, target_path, bare=True, errstream=errstream) as r: self.assertEqual(r.path, target_path) with Repo(target_path) as r: r.head() self.assertRaises(NoIndexPresent, r.open_index) self.assertFalse(b'f1' in os.listdir(target_path)) self.assertFalse(b'f2' in os.listdir(target_path)) def test_no_checkout_with_bare(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)]} (c1, ) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id self.repo.refs[b"HEAD"] = c1.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) self.assertRaises( ValueError, porcelain.clone, self.repo.path, target_path, checkout=True, bare=True, errstream=errstream) def test_no_head_no_checkout(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)]} (c1, ) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) errstream = BytesIO() r = porcelain.clone( self.repo.path, target_path, checkout=True, errstream=errstream) r.close() def test_no_head_no_checkout_outstream_errstream_autofallback(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)]} (c1, ) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) errstream = porcelain.NoneStream() r = porcelain.clone( self.repo.path, target_path, checkout=True, errstream=errstream) r.close() def test_source_broken(self): target_path = tempfile.mkdtemp() self.assertRaises( Exception, porcelain.clone, '/nonexistant/repo', target_path) self.assertFalse(os.path.exists(target_path)) class InitTests(TestCase): def test_non_bare(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) porcelain.init(repo_dir) def test_bare(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) porcelain.init(repo_dir, bare=True) class AddTests(PorcelainTestCase): def test_add_default_paths(self): # create a file for initial commit fullpath = os.path.join(self.repo.path, 'blah') with open(fullpath, 'w') as f: f.write("\n") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Add a second test file and a file in a directory with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("\n") os.mkdir(os.path.join(self.repo.path, 'adir')) with open(os.path.join(self.repo.path, 'adir', 'afile'), 'w') as f: f.write("\n") cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.add(self.repo.path) finally: os.chdir(cwd) # Check that foo was added and nothing in .git was modified index = self.repo.open_index() self.assertEqual(sorted(index), [b'adir/afile', b'blah', b'foo']) def test_add_default_paths_subdir(self): os.mkdir(os.path.join(self.repo.path, 'foo')) with open(os.path.join(self.repo.path, 'blah'), 'w') as f: f.write("\n") with open(os.path.join(self.repo.path, 'foo', 'blie'), 'w') as f: f.write("\n") cwd = os.getcwd() try: os.chdir(os.path.join(self.repo.path, 'foo')) porcelain.add(repo=self.repo.path) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') finally: os.chdir(cwd) index = self.repo.open_index() self.assertEqual(sorted(index), [b'foo/blie']) def test_add_file(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) self.assertIn(b"foo", self.repo.open_index()) def test_add_ignored(self): with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write("foo") with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("BAR") with open(os.path.join(self.repo.path, 'bar'), 'w') as f: f.write("BAR") (added, ignored) = porcelain.add(self.repo.path, paths=[ os.path.join(self.repo.path, "foo"), os.path.join(self.repo.path, "bar")]) self.assertIn(b"bar", self.repo.open_index()) self.assertEqual(set(['bar']), set(added)) self.assertEqual(set(['foo']), ignored) def test_add_file_absolute_path(self): # Absolute paths are (not yet) supported with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("BAR") porcelain.add(self.repo, paths=[os.path.join(self.repo.path, "foo")]) self.assertIn(b"foo", self.repo.open_index()) def test_add_not_in_repo(self): with open(os.path.join(self.test_dir, 'foo'), 'w') as f: f.write("BAR") self.assertRaises( ValueError, porcelain.add, self.repo, paths=[os.path.join(self.test_dir, "foo")]) self.assertRaises( ValueError, porcelain.add, self.repo, paths=["../foo"]) self.assertEqual([], list(self.repo.open_index())) def test_add_file_clrf_conversion(self): # Set the right configuration to the repo c = self.repo.get_config() c.set("core", "autocrlf", "input") c.write_to_path() # Add a file with CRLF line-ending fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'wb') as f: f.write(b"line1\r\nline2") porcelain.add(self.repo.path, paths=[fullpath]) # The line-endings should have been converted to LF index = self.repo.open_index() self.assertIn(b"foo", index) entry = index[b"foo"] blob = self.repo[entry.sha] self.assertEqual(blob.data, b"line1\nline2") class RemoveTests(PorcelainTestCase): def test_remove_file(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo, message=b'test', author=b'test ', committer=b'test ') self.assertTrue(os.path.exists(os.path.join(self.repo.path, 'foo'))) cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.remove(self.repo.path, paths=["foo"]) finally: os.chdir(cwd) self.assertFalse(os.path.exists(os.path.join(self.repo.path, 'foo'))) def test_remove_file_staged(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.add(self.repo.path, paths=[fullpath]) self.assertRaises(Exception, porcelain.rm, self.repo.path, paths=["foo"]) finally: os.chdir(cwd) class LogTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream) self.assertEqual(3, outstream.getvalue().count("-" * 50)) def test_max_entries(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream, max_entries=1) self.assertEqual(1, outstream.getvalue().count("-" * 50)) class ShowTests(PorcelainTestCase): def test_nolist(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.show(self.repo.path, objects=c3.id, outstream=outstream) self.assertTrue(outstream.getvalue().startswith("-" * 50)) def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.show(self.repo.path, objects=[c3.id], outstream=outstream) self.assertTrue(outstream.getvalue().startswith("-" * 50)) def test_blob(self): b = Blob.from_string(b"The Foo\n") self.repo.object_store.add_object(b) outstream = StringIO() porcelain.show(self.repo.path, objects=[b.id], outstream=outstream) self.assertEqual(outstream.getvalue(), "The Foo\n") def test_commit_no_parent(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) self.repo.object_store.add_objects([(a, None), (ta, None), (ca, None)]) outstream = StringIO() porcelain.show(self.repo.path, objects=[ca.id], outstream=outstream) self.assertMultiLineEqual(outstream.getvalue(), """\ -------------------------------------------------- commit: 344da06c1bb85901270b3e8875c988a027ec087d Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git a/somename b/somename new file mode 100644 index 0000000..ea5c7bf --- /dev/null +++ b/somename @@ -0,0 +1 @@ +The Foo """) def test_tag(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) self.repo.object_store.add_objects([(a, None), (ta, None), (ca, None)]) porcelain.tag_create( self.repo.path, b"tryme", b'foo ', b'bar', annotated=True, objectish=ca.id, tag_time=1552854211, tag_timezone=0) outstream = StringIO() porcelain.show(self.repo, objects=[b'refs/tags/tryme'], outstream=outstream) self.maxDiff = None self.assertMultiLineEqual(outstream.getvalue(), """\ Tagger: foo Date: Sun Mar 17 2019 20:23:31 +0000 bar -------------------------------------------------- commit: 344da06c1bb85901270b3e8875c988a027ec087d Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git a/somename b/somename new file mode 100644 index 0000000..ea5c7bf --- /dev/null +++ b/somename @@ -0,0 +1 @@ +The Foo """) def test_commit_with_change(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) b = Blob.from_string(b"The Bar\n") tb = Tree() tb.add(b"somename", 0o100644, b.id) cb = make_commit(tree=tb.id, parents=[ca.id]) self.repo.object_store.add_objects( [(a, None), (b, None), (ta, None), (tb, None), (ca, None), (cb, None)]) outstream = StringIO() porcelain.show(self.repo.path, objects=[cb.id], outstream=outstream) self.assertMultiLineEqual(outstream.getvalue(), """\ -------------------------------------------------- commit: 2c6b6c9cb72c130956657e1fdae58e5b103744fa Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git a/somename b/somename index ea5c7bf..fd38bcb 100644 --- a/somename +++ b/somename @@ -1 +1 @@ -The Foo +The Bar """) class SymbolicRefTests(PorcelainTestCase): def test_set_wrong_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id self.assertRaises(ValueError, porcelain.symbolic_ref, self.repo.path, b'foobar') def test_set_force_wrong_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.symbolic_ref(self.repo.path, b'force_foobar', force=True) # test if we actually changed the file with self.repo.get_named_file('HEAD') as f: new_ref = f.read() self.assertEqual(new_ref, b'ref: refs/heads/force_foobar\n') def test_set_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.symbolic_ref(self.repo.path, b'master') def test_set_symbolic_ref_other_than_master(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]], attrs=dict(refs='develop')) self.repo.refs[b"HEAD"] = c3.id self.repo.refs[b"refs/heads/develop"] = c3.id porcelain.symbolic_ref(self.repo.path, b'develop') # test if we actually changed the file with self.repo.get_named_file('HEAD') as f: new_ref = f.read() self.assertEqual(new_ref, b'ref: refs/heads/develop\n') class DiffTreeTests(PorcelainTestCase): def test_empty(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = BytesIO() porcelain.diff_tree(self.repo.path, c2.tree, c3.tree, outstream=outstream) self.assertEqual(outstream.getvalue(), b"") class CommitTreeTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) b = Blob() b.data = b"foo the bar" t = Tree() t.add(b"somename", 0o100644, b.id) self.repo.object_store.add_object(t) self.repo.object_store.add_object(b) sha = porcelain.commit_tree( self.repo.path, t.id, message=b"Withcommit.", author=b"Joe ", committer=b"Jane ") self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) class RevListTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) outstream = BytesIO() porcelain.rev_list( self.repo.path, [c3.id], outstream=outstream) self.assertEqual( c3.id + b"\n" + c2.id + b"\n" + c1.id + b"\n", outstream.getvalue()) class TagCreateTests(PorcelainTestCase): def test_annotated(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, b"tryme", b'foo ', b'bar', annotated=True) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) tag = self.repo[b'refs/tags/tryme'] self.assertTrue(isinstance(tag, Tag)) self.assertEqual(b"foo ", tag.tagger) self.assertEqual(b"bar", tag.message) self.assertLess(time.time() - tag.tag_time, 5) def test_unannotated(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, b"tryme", annotated=False) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) self.repo[b'refs/tags/tryme'] self.assertEqual(list(tags.values()), [self.repo.head()]) def test_unannotated_unicode(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, "tryme", annotated=False) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) self.repo[b'refs/tags/tryme'] self.assertEqual(list(tags.values()), [self.repo.head()]) class TagListTests(PorcelainTestCase): def test_empty(self): tags = porcelain.tag_list(self.repo.path) self.assertEqual([], tags) def test_simple(self): self.repo.refs[b"refs/tags/foo"] = b"aa" * 20 self.repo.refs[b"refs/tags/bar/bla"] = b"bb" * 20 tags = porcelain.tag_list(self.repo.path) self.assertEqual([b"bar/bla", b"foo"], tags) class TagDeleteTests(PorcelainTestCase): def test_simple(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.tag_create(self.repo, b'foo') self.assertTrue(b"foo" in porcelain.tag_list(self.repo)) porcelain.tag_delete(self.repo, b'foo') self.assertFalse(b"foo" in porcelain.tag_list(self.repo)) class ResetTests(PorcelainTestCase): def test_hard_head(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit(self.repo.path, message=b"Some message", committer=b"Jane ", author=b"John ") with open(os.path.join(self.repo.path, 'foo'), 'wb') as f: f.write(b"OOH") porcelain.reset(self.repo, "hard", b"HEAD") index = self.repo.open_index() changes = list(tree_changes(self.repo, index.commit(self.repo.object_store), self.repo[b'HEAD'].tree)) self.assertEqual([], changes) def test_hard_commit(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) sha = porcelain.commit(self.repo.path, message=b"Some message", committer=b"Jane ", author=b"John ") with open(fullpath, 'wb') as f: f.write(b"BAZ") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit(self.repo.path, message=b"Some other message", committer=b"Jane ", author=b"John ") porcelain.reset(self.repo, "hard", sha) index = self.repo.open_index() changes = list(tree_changes(self.repo, index.commit(self.repo.object_store), self.repo[sha].tree)) self.assertEqual([], changes) class PushTests(PorcelainTestCase): def test_simple(self): """ Basic test of porcelain push where self.repo is the remote. First clone the remote, commit a file to the clone, then push the changes back to the remote. """ outstream = BytesIO() errstream = BytesIO() porcelain.commit(repo=self.repo.path, message=b'init', author=b'author ', committer=b'committer ') # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.clone(self.repo.path, target=clone_path, errstream=errstream) try: self.assertEqual(target_repo[b'HEAD'], self.repo[b'HEAD']) finally: target_repo.close() # create a second file to be pushed back to origin handle, fullpath = tempfile.mkstemp(dir=clone_path) os.close(handle) porcelain.add(repo=clone_path, paths=[fullpath]) porcelain.commit(repo=clone_path, message=b'push', author=b'author ', committer=b'committer ') # Setup a non-checked out branch in the remote refs_path = b"refs/heads/foo" new_id = self.repo[b'HEAD'].id self.assertNotEqual(new_id, ZERO_SHA) self.repo.refs[refs_path] = new_id # Push to the remote porcelain.push(clone_path, self.repo.path, b"HEAD:" + refs_path, outstream=outstream, errstream=errstream) # Check that the target and source with Repo(clone_path) as r_clone: self.assertEqual({ b'HEAD': new_id, b'refs/heads/foo': r_clone[b'HEAD'].id, b'refs/heads/master': new_id, }, self.repo.get_refs()) self.assertEqual(r_clone[b'HEAD'].id, self.repo[refs_path].id) # Get the change in the target repo corresponding to the add # this will be in the foo branch. change = list(tree_changes(self.repo, self.repo[b'HEAD'].tree, self.repo[b'refs/heads/foo'].tree))[0] self.assertEqual(os.path.basename(fullpath), change.new.path.decode('ascii')) def test_delete(self): """Basic test of porcelain push, removing a branch. """ outstream = BytesIO() errstream = BytesIO() porcelain.commit(repo=self.repo.path, message=b'init', author=b'author ', committer=b'committer ') # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.clone(self.repo.path, target=clone_path, errstream=errstream) target_repo.close() # Setup a non-checked out branch in the remote refs_path = b"refs/heads/foo" new_id = self.repo[b'HEAD'].id self.assertNotEqual(new_id, ZERO_SHA) self.repo.refs[refs_path] = new_id # Push to the remote porcelain.push(clone_path, self.repo.path, b":" + refs_path, outstream=outstream, errstream=errstream) self.assertEqual({ b'HEAD': new_id, b'refs/heads/master': new_id, }, self.repo.get_refs()) class PullTests(PorcelainTestCase): def setUp(self): super(PullTests, self).setUp() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Setup target repo self.target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.target_path) target_repo = porcelain.clone(self.repo.path, target=self.target_path, errstream=BytesIO()) target_repo.close() # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2 ', committer=b'test2 ') self.assertTrue(b'refs/heads/master' in self.repo.refs) self.assertTrue(b'refs/heads/master' in target_repo.refs) def test_simple(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull(self.target_path, self.repo.path, b'refs/heads/master', outstream=outstream, errstream=errstream) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b'HEAD'].id, self.repo[b'HEAD'].id) def test_no_refspec(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull(self.target_path, self.repo.path, outstream=outstream, errstream=errstream) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b'HEAD'].id, self.repo[b'HEAD'].id) def test_no_remote_location(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull(self.target_path, refspecs=b'refs/heads/master', outstream=outstream, errstream=errstream) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b'HEAD'].id, self.repo[b'HEAD'].id) class StatusTests(PorcelainTestCase): def test_empty(self): results = porcelain.status(self.repo) self.assertEqual( {'add': [], 'delete': [], 'modify': []}, results.staged) self.assertEqual([], results.unstaged) def test_status_base(self): """Integration test for `status` functionality.""" # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') # modify access and modify time of path os.utime(fullpath, (0, 0)) with open(fullpath, 'wb') as f: f.write(b'stuff') # Make a dummy file and stage it filename_add = 'bar' fullpath = os.path.join(self.repo.path, filename_add) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) results = porcelain.status(self.repo) self.assertEqual(results.staged['add'][0], filename_add.encode('ascii')) self.assertEqual(results.unstaged, [b'foo']) def test_status_all(self): del_path = os.path.join(self.repo.path, 'foo') mod_path = os.path.join(self.repo.path, 'bar') add_path = os.path.join(self.repo.path, 'baz') us_path = os.path.join(self.repo.path, 'blye') ut_path = os.path.join(self.repo.path, 'blyat') with open(del_path, 'w') as f: f.write('origstuff') with open(mod_path, 'w') as f: f.write('origstuff') with open(us_path, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[del_path, mod_path, us_path]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') porcelain.remove(self.repo.path, [del_path]) with open(add_path, 'w') as f: f.write('origstuff') with open(mod_path, 'w') as f: f.write('more_origstuff') with open(us_path, 'w') as f: f.write('more_origstuff') porcelain.add(repo=self.repo.path, paths=[add_path, mod_path]) with open(us_path, 'w') as f: f.write('\norigstuff') with open(ut_path, 'w') as f: f.write('origstuff') results = porcelain.status(self.repo.path) self.assertDictEqual( {'add': [b'baz'], 'delete': [b'foo'], 'modify': [b'bar']}, results.staged) self.assertListEqual(results.unstaged, [b'blye']) self.assertListEqual(results.untracked, ['blyat']) def test_status_crlf_mismatch(self): # First make a commit as if the file has been added on a Linux system # or with core.autocrlf=True file_path = os.path.join(self.repo.path, 'crlf') with open(file_path, 'wb') as f: f.write(b'line1\nline2') porcelain.add(repo=self.repo.path, paths=[file_path]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') # Then update the file as if it was created by CGit on a Windows # system with core.autocrlf=true with open(file_path, 'wb') as f: f.write(b'line1\r\nline2') results = porcelain.status(self.repo) self.assertDictEqual( {'add': [], 'delete': [], 'modify': []}, results.staged) self.assertListEqual(results.unstaged, [b'crlf']) self.assertListEqual(results.untracked, []) def test_status_crlf_convert(self): # First make a commit as if the file has been added on a Linux system # or with core.autocrlf=True file_path = os.path.join(self.repo.path, 'crlf') with open(file_path, 'wb') as f: f.write(b'line1\nline2') porcelain.add(repo=self.repo.path, paths=[file_path]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') # Then update the file as if it was created by CGit on a Windows # system with core.autocrlf=true with open(file_path, 'wb') as f: f.write(b'line1\r\nline2') # TODO: It should be set automatically by looking at the configuration c = self.repo.get_config() c.set("core", "autocrlf", True) c.write_to_path() results = porcelain.status(self.repo) self.assertDictEqual( {'add': [], 'delete': [], 'modify': []}, results.staged) self.assertListEqual(results.unstaged, []) self.assertListEqual(results.untracked, []) def test_get_tree_changes_add(self): """Unit test for get_tree_changes add.""" # Make a dummy file, stage filename = 'bar' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes['add'][0], filename.encode('ascii')) self.assertEqual(len(changes['add']), 1) self.assertEqual(len(changes['modify']), 0) self.assertEqual(len(changes['delete']), 0) def test_get_tree_changes_modify(self): """Unit test for get_tree_changes modify.""" # Make a dummy file, stage, commit, modify filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') with open(fullpath, 'w') as f: f.write('otherstuff') porcelain.add(repo=self.repo.path, paths=fullpath) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes['modify'][0], filename.encode('ascii')) self.assertEqual(len(changes['add']), 0) self.assertEqual(len(changes['modify']), 1) self.assertEqual(len(changes['delete']), 0) def test_get_tree_changes_delete(self): """Unit test for get_tree_changes delete.""" # Make a dummy file, stage, commit, remove filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.remove(repo=self.repo.path, paths=[filename]) finally: os.chdir(cwd) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes['delete'][0], filename.encode('ascii')) self.assertEqual(len(changes['add']), 0) self.assertEqual(len(changes['modify']), 0) self.assertEqual(len(changes['delete']), 1) def test_get_untracked_paths(self): with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('ignored\n') with open(os.path.join(self.repo.path, 'ignored'), 'w') as f: f.write('blah\n') with open(os.path.join(self.repo.path, 'notignored'), 'w') as f: f.write('blah\n') self.assertEqual( set(['ignored', 'notignored', '.gitignore']), set(porcelain.get_untracked_paths(self.repo.path, self.repo.path, self.repo.open_index()))) self.assertEqual(set(['.gitignore', 'notignored']), set(porcelain.status(self.repo).untracked)) self.assertEqual(set(['.gitignore', 'notignored', 'ignored']), set(porcelain.status(self.repo, ignored=True) .untracked)) def test_get_untracked_paths_nested(self): with open(os.path.join(self.repo.path, 'notignored'), 'w') as f: f.write('blah\n') subrepo = Repo.init(os.path.join(self.repo.path, 'nested'), mkdir=True) with open(os.path.join(subrepo.path, 'another'), 'w') as f: f.write('foo\n') self.assertEqual( set(['notignored']), set(porcelain.get_untracked_paths(self.repo.path, self.repo.path, self.repo.open_index()))) self.assertEqual( set(['another']), set(porcelain.get_untracked_paths(subrepo.path, subrepo.path, subrepo.open_index()))) # TODO(jelmer): Add test for dulwich.porcelain.daemon class UploadPackTests(PorcelainTestCase): """Tests for upload_pack.""" def test_upload_pack(self): outf = BytesIO() exitcode = porcelain.upload_pack( self.repo.path, BytesIO(b"0000"), outf) outlines = outf.getvalue().splitlines() self.assertEqual([b"0000"], outlines) self.assertEqual(0, exitcode) class ReceivePackTests(PorcelainTestCase): """Tests for receive_pack.""" def test_receive_pack(self): filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) self.repo.do_commit(message=b'test status', author=b'author ', committer=b'committer ', author_timestamp=1402354300, commit_timestamp=1402354300, author_timezone=0, commit_timezone=0) outf = BytesIO() exitcode = porcelain.receive_pack( self.repo.path, BytesIO(b"0000"), outf) outlines = outf.getvalue().splitlines() self.assertEqual([ b'0091319b56ce3aee2d489f759736a79cc552c9bb86d9 HEAD\x00 report-status ' # noqa: E501 b'delete-refs quiet ofs-delta side-band-64k ' b'no-done symref=HEAD:refs/heads/master', b'003f319b56ce3aee2d489f759736a79cc552c9bb86d9 refs/heads/master', b'0000'], outlines) self.assertEqual(0, exitcode) class BranchListTests(PorcelainTestCase): def test_standard(self): self.assertEqual(set([]), set(porcelain.branch_list(self.repo))) def test_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertEqual( set([b"master", b"foo"]), set(porcelain.branch_list(self.repo))) class BranchCreateTests(PorcelainTestCase): def test_branch_exists(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertRaises(KeyError, porcelain.branch_create, self.repo, b"foo") porcelain.branch_create(self.repo, b"foo", force=True) def test_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertEqual( set([b"master", b"foo"]), set(porcelain.branch_list(self.repo))) class BranchDeleteTests(PorcelainTestCase): def test_simple(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b'foo') self.assertTrue(b"foo" in porcelain.branch_list(self.repo)) porcelain.branch_delete(self.repo, b'foo') self.assertFalse(b"foo" in porcelain.branch_list(self.repo)) def test_simple_unicode(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, 'foo') self.assertTrue(b"foo" in porcelain.branch_list(self.repo)) porcelain.branch_delete(self.repo, 'foo') self.assertFalse(b"foo" in porcelain.branch_list(self.repo)) class FetchTests(PorcelainTestCase): def test_simple(self): outstream = BytesIO() errstream = BytesIO() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Setup target repo target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) target_repo = porcelain.clone(self.repo.path, target=target_path, errstream=errstream) # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2 ', committer=b'test2 ') self.assertFalse(self.repo[b'HEAD'].id in target_repo) target_repo.close() # Fetch changes into the cloned repo porcelain.fetch(target_path, self.repo.path, outstream=outstream, errstream=errstream) # Assert that fetch updated the local image of the remote self.assert_correct_remote_refs( target_repo.get_refs(), self.repo.get_refs()) # Check the target repo for pushed changes with Repo(target_path) as r: self.assertTrue(self.repo[b'HEAD'].id in r) def test_with_remote_name(self): remote_name = b'origin' outstream = BytesIO() errstream = BytesIO() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Setup target repo target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) target_repo = porcelain.clone(self.repo.path, target=target_path, errstream=errstream) # Capture current refs target_refs = target_repo.get_refs() # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2 ', committer=b'test2 ') self.assertFalse(self.repo[b'HEAD'].id in target_repo) target_repo.close() # Fetch changes into the cloned repo porcelain.fetch(target_path, self.repo.path, remote_name=remote_name, outstream=outstream, errstream=errstream) # Assert that fetch updated the local image of the remote self.assert_correct_remote_refs( target_repo.get_refs(), self.repo.get_refs()) # Check the target repo for pushed changes, as well as updates # for the refs with Repo(target_path) as r: self.assertTrue(self.repo[b'HEAD'].id in r) self.assertNotEqual(self.repo.get_refs(), target_refs) def assert_correct_remote_refs( self, local_refs, remote_refs, remote_name=b'origin'): """Assert that known remote refs corresponds to actual remote refs.""" local_ref_prefix = b'refs/heads' remote_ref_prefix = b'refs/remotes/' + remote_name locally_known_remote_refs = { k[len(remote_ref_prefix) + 1:]: v for k, v in local_refs.items() if k.startswith(remote_ref_prefix)} normalized_remote_refs = { k[len(local_ref_prefix) + 1:]: v for k, v in remote_refs.items() if k.startswith(local_ref_prefix)} self.assertEqual(locally_known_remote_refs, normalized_remote_refs) class RepackTests(PorcelainTestCase): def test_empty(self): porcelain.repack(self.repo) def test_simple(self): handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.repack(self.repo) class LsTreeTests(PorcelainTestCase): def test_empty(self): porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual(f.getvalue(), "") def test_simple(self): # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual( f.getvalue(), '100644 blob 8b82634d7eae019850bb883f06abf428c58bc9aa\tfoo\n') def test_recursive(self): # Create a directory then write a dummy file in it dirpath = os.path.join(self.repo.path, 'adir') filepath = os.path.join(dirpath, 'afile') os.mkdir(dirpath) with open(filepath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[filepath]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual( f.getvalue(), '40000 tree b145cc69a5e17693e24d8a7be0016ed8075de66d\tadir\n') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f, recursive=True) self.assertEqual( f.getvalue(), '40000 tree b145cc69a5e17693e24d8a7be0016ed8075de66d\tadir\n' '100644 blob 8b82634d7eae019850bb883f06abf428c58bc9aa\tadir' '/afile\n') class LsRemoteTests(PorcelainTestCase): def test_empty(self): self.assertEqual({}, porcelain.ls_remote(self.repo.path)) def test_some(self): cid = porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') self.assertEqual({ b'refs/heads/master': cid, b'HEAD': cid}, porcelain.ls_remote(self.repo.path)) class LsFilesTests(PorcelainTestCase): def test_empty(self): self.assertEqual([], list(porcelain.ls_files(self.repo))) def test_simple(self): # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[fullpath]) self.assertEqual([b'foo'], list(porcelain.ls_files(self.repo))) class RemoteAddTests(PorcelainTestCase): def test_new(self): porcelain.remote_add( self.repo, 'jelmer', 'git://jelmer.uk/code/dulwich') c = self.repo.get_config() self.assertEqual( c.get((b'remote', b'jelmer'), b'url'), b'git://jelmer.uk/code/dulwich') def test_exists(self): porcelain.remote_add( self.repo, 'jelmer', 'git://jelmer.uk/code/dulwich') self.assertRaises(porcelain.RemoteExists, porcelain.remote_add, self.repo, 'jelmer', 'git://jelmer.uk/code/dulwich') class CheckIgnoreTests(PorcelainTestCase): def test_check_ignored(self): with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('foo') foo_path = os.path.join(self.repo.path, 'foo') with open(foo_path, 'w') as f: f.write('BAR') bar_path = os.path.join(self.repo.path, 'bar') with open(bar_path, 'w') as f: f.write('BAR') self.assertEqual( ['foo'], list(porcelain.check_ignore(self.repo, [foo_path]))) self.assertEqual( [], list(porcelain.check_ignore(self.repo, [bar_path]))) def test_check_added_abs(self): path = os.path.join(self.repo.path, 'foo') with open(path, 'w') as f: f.write('BAR') self.repo.stage(['foo']) with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('foo\n') self.assertEqual( [], list(porcelain.check_ignore(self.repo, [path]))) self.assertEqual( ['foo'], list(porcelain.check_ignore(self.repo, [path], no_index=True))) def test_check_added_rel(self): with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write('BAR') self.repo.stage(['foo']) with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('foo\n') cwd = os.getcwd() os.mkdir(os.path.join(self.repo.path, 'bar')) os.chdir(os.path.join(self.repo.path, 'bar')) try: self.assertEqual( list(porcelain.check_ignore(self.repo, ['../foo'])), []) self.assertEqual(['../foo'], list( porcelain.check_ignore(self.repo, ['../foo'], no_index=True))) finally: os.chdir(cwd) class UpdateHeadTests(PorcelainTestCase): def test_set_to_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah") self.assertEqual(c1.id, self.repo.head()) self.assertEqual(b'ref: refs/heads/blah', self.repo.refs.read_ref(b'HEAD')) def test_set_to_branch_detached(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah", detached=True) self.assertEqual(c1.id, self.repo.head()) self.assertEqual(c1.id, self.repo.refs.read_ref(b'HEAD')) def test_set_to_commit_detached(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, c1.id, detached=True) self.assertEqual(c1.id, self.repo.head()) self.assertEqual(c1.id, self.repo.refs.read_ref(b'HEAD')) def test_set_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah", new_branch="bar") self.assertEqual(c1.id, self.repo.head()) self.assertEqual(b'ref: refs/heads/bar', self.repo.refs.read_ref(b'HEAD')) class MailmapTests(PorcelainTestCase): def test_no_mailmap(self): self.assertEqual( b'Jelmer Vernooij ', porcelain.check_mailmap( self.repo, b'Jelmer Vernooij ')) def test_mailmap_lookup(self): with open(os.path.join(self.repo.path, '.mailmap'), 'wb') as f: f.write(b"""\ Jelmer Vernooij """) self.assertEqual( b'Jelmer Vernooij ', porcelain.check_mailmap( self.repo, b'Jelmer Vernooij ')) class FsckTests(PorcelainTestCase): def test_none(self): self.assertEqual( [], list(porcelain.fsck(self.repo))) def test_git_dir(self): obj = Tree() a = Blob() a.data = b"foo" obj.add(b".git", 0o100644, a.id) self.repo.object_store.add_objects( [(a, None), (obj, None)]) self.assertEqual( [(obj.id, 'invalid name .git')], [(sha, str(e)) for (sha, e) in porcelain.fsck(self.repo)]) class DescribeTests(PorcelainTestCase): def test_no_commits(self): self.assertRaises(KeyError, porcelain.describe, self.repo.path) def test_single_commit(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") self.assertEqual( 'g{}'.format(sha[:7].decode('ascii')), porcelain.describe(self.repo.path)) def test_tag(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") porcelain.tag_create(self.repo.path, b"tryme", b'foo ', b'bar', annotated=True) self.assertEqual( "tryme", porcelain.describe(self.repo.path)) def test_tag_and_commit(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") porcelain.tag_create(self.repo.path, b"tryme", b'foo ', b'bar', annotated=True) with open(fullpath, 'w') as f: f.write("BAR2") porcelain.add(repo=self.repo.path, paths=[fullpath]) sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") self.assertEqual( 'tryme-1-g{}'.format(sha[:7].decode('ascii')), porcelain.describe(self.repo.path)) class HelperTests(PorcelainTestCase): def test_path_to_tree_path_base(self): self.assertEqual( b'bar', porcelain.path_to_tree_path('/home/foo', '/home/foo/bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path('.', './bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path('.', 'bar')) cwd = os.getcwd() self.assertEqual( b'bar', porcelain.path_to_tree_path('.', os.path.join(cwd, 'bar'))) self.assertEqual(b'bar', porcelain.path_to_tree_path(cwd, 'bar')) def test_path_to_tree_path_syntax(self): self.assertEqual(b'bar', porcelain.path_to_tree_path(b'.', './bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path('.', b'./bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path(b'.', b'./bar')) def test_path_to_tree_path_error(self): with self.assertRaises(ValueError): porcelain.path_to_tree_path('/home/foo/', '/home/bar/baz') def test_path_to_tree_path_rel(self): cwd = os.getcwd() os.mkdir(os.path.join(self.repo.path, 'foo')) os.mkdir(os.path.join(self.repo.path, 'foo/bar')) try: os.chdir(os.path.join(self.repo.path, 'foo/bar')) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( '..', 'baz')) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( os.path.join(os.getcwd(), '..'), os.path.join(os.getcwd(), 'baz'))) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( '..', os.path.join(os.getcwd(), 'baz'))) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( os.path.join(os.getcwd(), '..'), 'baz')) finally: os.chdir(cwd) class GetObjectByPathTests(PorcelainTestCase): def test_simple(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") self.assertEqual( b"BAR", porcelain.get_object_by_path(self.repo, 'foo').data) self.assertEqual( b"BAR", porcelain.get_object_by_path(self.repo, b'foo').data) def test_encoding(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ", encoding=b"utf-8") self.assertEqual( b"BAR", porcelain.get_object_by_path(self.repo, 'foo').data) self.assertEqual( b"BAR", porcelain.get_object_by_path(self.repo, b'foo').data) def test_missing(self): self.assertRaises( KeyError, porcelain.get_object_by_path, self.repo, 'foo') class WriteTreeTests(PorcelainTestCase): def test_simple(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) self.assertEqual( b'd2092c8a9f311f0311083bf8d177f2ca0ab5b241', porcelain.write_tree(self.repo)) class ActiveBranchTests(PorcelainTestCase): def test_simple(self): self.assertEqual(b'master', porcelain.active_branch(self.repo)) diff --git a/dulwich/web.py b/dulwich/web.py index eb66304b..47622945 100644 --- a/dulwich/web.py +++ b/dulwich/web.py @@ -1,521 +1,518 @@ # web.py -- WSGI smart-http server # Copyright (C) 2010 Google, Inc. # Copyright (C) 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. # """HTTP server for dulwich that implements the git smart HTTP protocol.""" from io import BytesIO import shutil import tempfile import gzip import os import re import sys import time from wsgiref.simple_server import ( WSGIRequestHandler, ServerHandler, WSGIServer, make_server, ) -try: - from urlparse import parse_qs -except ImportError: - from urllib.parse import parse_qs +from urllib.parse import parse_qs from dulwich import log_utils from dulwich.protocol import ( ReceivableProtocol, ) from dulwich.repo import ( NotGitRepository, Repo, ) from dulwich.server import ( DictBackend, DEFAULT_HANDLERS, generate_info_refs, generate_objects_info_packs, ) logger = log_utils.getLogger(__name__) # HTTP error strings HTTP_OK = '200 OK' HTTP_NOT_FOUND = '404 Not Found' HTTP_FORBIDDEN = '403 Forbidden' HTTP_ERROR = '500 Internal Server Error' def date_time_string(timestamp=None): # From BaseHTTPRequestHandler.date_time_string in BaseHTTPServer.py in the # Python 2.6.5 standard library, following modifications: # - Made a global rather than an instance method. # - weekdayname and monthname are renamed and locals rather than class # variables. # Copyright (c) 2001-2010 Python Software Foundation; All Rights Reserved weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] months = [None, 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] if timestamp is None: timestamp = time.time() year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp) return '%s, %02d %3s %4d %02d:%02d:%02d GMD' % ( weekdays[wd], day, months[month], year, hh, mm, ss) def url_prefix(mat): """Extract the URL prefix from a regex match. Args: mat: A regex match object. Returns: The URL prefix, defined as the text before the match in the original string. Normalized to start with one leading slash and end with zero. """ return '/' + mat.string[:mat.start()].strip('/') def get_repo(backend, mat): """Get a Repo instance for the given backend and URL regex match.""" return backend.open_repository(url_prefix(mat)) def send_file(req, f, content_type): """Send a file-like object to the request output. Args: req: The HTTPGitRequest object to send output to. f: An open file-like object to send; will be closed. content_type: The MIME type for the file. Returns: Iterator over the contents of the file, as chunks. """ if f is None: yield req.not_found('File not found') return try: req.respond(HTTP_OK, content_type) while True: data = f.read(10240) if not data: break yield data except IOError: yield req.error('Error reading file') finally: f.close() def _url_to_path(url): return url.replace('/', os.path.sep) def get_text_file(req, backend, mat): req.nocache() path = _url_to_path(mat.group()) logger.info('Sending plain text file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'text/plain') def get_loose_object(req, backend, mat): sha = (mat.group(1) + mat.group(2)).encode('ascii') logger.info('Sending loose object %s', sha) object_store = get_repo(backend, mat).object_store if not object_store.contains_loose(sha): yield req.not_found('Object not found') return try: data = object_store[sha].as_legacy_object() except IOError: yield req.error('Error reading object') return req.cache_forever() req.respond(HTTP_OK, 'application/x-git-loose-object') yield data def get_pack_file(req, backend, mat): req.cache_forever() path = _url_to_path(mat.group()) logger.info('Sending pack file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'application/x-git-packed-objects') def get_idx_file(req, backend, mat): req.cache_forever() path = _url_to_path(mat.group()) logger.info('Sending pack file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'application/x-git-packed-objects-toc') def get_info_refs(req, backend, mat): params = parse_qs(req.environ['QUERY_STRING']) service = params.get('service', [None])[0] try: repo = get_repo(backend, mat) except NotGitRepository as e: yield req.not_found(str(e)) return if service and not req.dumb: handler_cls = req.handlers.get(service.encode('ascii'), None) if handler_cls is None: yield req.forbidden('Unsupported service') return req.nocache() write = req.respond( HTTP_OK, 'application/x-%s-advertisement' % service) proto = ReceivableProtocol(BytesIO().read, write) handler = handler_cls(backend, [url_prefix(mat)], proto, http_req=req, advertise_refs=True) handler.proto.write_pkt_line( b'# service=' + service.encode('ascii') + b'\n') handler.proto.write_pkt_line(None) handler.handle() else: # non-smart fallback # TODO: select_getanyfile() (see http-backend.c) req.nocache() req.respond(HTTP_OK, 'text/plain') logger.info('Emulating dumb info/refs') for text in generate_info_refs(repo): yield text def get_info_packs(req, backend, mat): req.nocache() req.respond(HTTP_OK, 'text/plain') logger.info('Emulating dumb info/packs') return generate_objects_info_packs(get_repo(backend, mat)) class _LengthLimitedFile(object): """Wrapper class to limit the length of reads from a file-like object. This is used to ensure EOF is read from the wsgi.input object once Content-Length bytes are read. This behavior is required by the WSGI spec but not implemented in wsgiref as of 2.5. """ def __init__(self, input, max_bytes): self._input = input self._bytes_avail = max_bytes def read(self, size=-1): if self._bytes_avail <= 0: return b'' if size == -1 or size > self._bytes_avail: size = self._bytes_avail self._bytes_avail -= size return self._input.read(size) # TODO: support more methods as necessary def handle_service_request(req, backend, mat): service = mat.group().lstrip('/') logger.info('Handling service request for %s', service) handler_cls = req.handlers.get(service.encode('ascii'), None) if handler_cls is None: yield req.forbidden('Unsupported service') return try: get_repo(backend, mat) except NotGitRepository as e: yield req.not_found(str(e)) return req.nocache() write = req.respond(HTTP_OK, 'application/x-%s-result' % service) proto = ReceivableProtocol(req.environ['wsgi.input'].read, write) # TODO(jelmer): Find a way to pass in repo, rather than having handler_cls # reopen. handler = handler_cls(backend, [url_prefix(mat)], proto, http_req=req) handler.handle() class HTTPGitRequest(object): """Class encapsulating the state of a single git HTTP request. :ivar environ: the WSGI environment for the request. """ def __init__(self, environ, start_response, dumb=False, handlers=None): self.environ = environ self.dumb = dumb self.handlers = handlers self._start_response = start_response self._cache_headers = [] self._headers = [] def add_header(self, name, value): """Add a header to the response.""" self._headers.append((name, value)) def respond(self, status=HTTP_OK, content_type=None, headers=None): """Begin a response with the given status and other headers.""" if headers: self._headers.extend(headers) if content_type: self._headers.append(('Content-Type', content_type)) self._headers.extend(self._cache_headers) return self._start_response(status, self._headers) def not_found(self, message): """Begin a HTTP 404 response and return the text of a message.""" self._cache_headers = [] logger.info('Not found: %s', message) self.respond(HTTP_NOT_FOUND, 'text/plain') return message.encode('ascii') def forbidden(self, message): """Begin a HTTP 403 response and return the text of a message.""" self._cache_headers = [] logger.info('Forbidden: %s', message) self.respond(HTTP_FORBIDDEN, 'text/plain') return message.encode('ascii') def error(self, message): """Begin a HTTP 500 response and return the text of a message.""" self._cache_headers = [] logger.error('Error: %s', message) self.respond(HTTP_ERROR, 'text/plain') return message.encode('ascii') def nocache(self): """Set the response to never be cached by the client.""" self._cache_headers = [ ('Expires', 'Fri, 01 Jan 1980 00:00:00 GMT'), ('Pragma', 'no-cache'), ('Cache-Control', 'no-cache, max-age=0, must-revalidate'), ] def cache_forever(self): """Set the response to be cached forever by the client.""" now = time.time() self._cache_headers = [ ('Date', date_time_string(now)), ('Expires', date_time_string(now + 31536000)), ('Cache-Control', 'public, max-age=31536000'), ] class HTTPGitApplication(object): """Class encapsulating the state of a git WSGI application. :ivar backend: the Backend object backing this application """ services = { ('GET', re.compile('/HEAD$')): get_text_file, ('GET', re.compile('/info/refs$')): get_info_refs, ('GET', re.compile('/objects/info/alternates$')): get_text_file, ('GET', re.compile('/objects/info/http-alternates$')): get_text_file, ('GET', re.compile('/objects/info/packs$')): get_info_packs, ('GET', re.compile('/objects/([0-9a-f]{2})/([0-9a-f]{38})$')): get_loose_object, ('GET', re.compile('/objects/pack/pack-([0-9a-f]{40})\\.pack$')): get_pack_file, ('GET', re.compile('/objects/pack/pack-([0-9a-f]{40})\\.idx$')): get_idx_file, ('POST', re.compile('/git-upload-pack$')): handle_service_request, ('POST', re.compile('/git-receive-pack$')): handle_service_request, } def __init__(self, backend, dumb=False, handlers=None, fallback_app=None): self.backend = backend self.dumb = dumb self.handlers = dict(DEFAULT_HANDLERS) self.fallback_app = fallback_app if handlers is not None: self.handlers.update(handlers) def __call__(self, environ, start_response): path = environ['PATH_INFO'] method = environ['REQUEST_METHOD'] req = HTTPGitRequest(environ, start_response, dumb=self.dumb, handlers=self.handlers) # environ['QUERY_STRING'] has qs args handler = None for smethod, spath in self.services.keys(): if smethod != method: continue mat = spath.search(path) if mat: handler = self.services[smethod, spath] break if handler is None: if self.fallback_app is not None: return self.fallback_app(environ, start_response) else: return [req.not_found('Sorry, that method is not supported')] return handler(req, self.backend, mat) class GunzipFilter(object): """WSGI middleware that unzips gzip-encoded requests before passing on to the underlying application. """ def __init__(self, application): self.app = application def __call__(self, environ, start_response): if environ.get('HTTP_CONTENT_ENCODING', '') == 'gzip': try: environ['wsgi.input'].tell() wsgi_input = environ['wsgi.input'] except (AttributeError, IOError, NotImplementedError): # The gzip implementation in the standard library of Python 2.x # requires working '.seek()' and '.tell()' methods on the input # stream. Read the data into a temporary file to work around # this limitation. wsgi_input = tempfile.SpooledTemporaryFile(16 * 1024 * 1024) shutil.copyfileobj(environ['wsgi.input'], wsgi_input) wsgi_input.seek(0) environ['wsgi.input'] = gzip.GzipFile( filename=None, fileobj=wsgi_input, mode='r') del environ['HTTP_CONTENT_ENCODING'] if 'CONTENT_LENGTH' in environ: del environ['CONTENT_LENGTH'] return self.app(environ, start_response) class LimitedInputFilter(object): """WSGI middleware that limits the input length of a request to that specified in Content-Length. """ def __init__(self, application): self.app = application def __call__(self, environ, start_response): # This is not necessary if this app is run from a conforming WSGI # server. Unfortunately, there's no way to tell that at this point. # TODO: git may used HTTP/1.1 chunked encoding instead of specifying # content-length content_length = environ.get('CONTENT_LENGTH', '') if content_length: environ['wsgi.input'] = _LengthLimitedFile( environ['wsgi.input'], int(content_length)) return self.app(environ, start_response) def make_wsgi_chain(*args, **kwargs): """Factory function to create an instance of HTTPGitApplication, correctly wrapped with needed middleware. """ app = HTTPGitApplication(*args, **kwargs) wrapped_app = LimitedInputFilter(GunzipFilter(app)) return wrapped_app class ServerHandlerLogger(ServerHandler): """ServerHandler that uses dulwich's logger for logging exceptions.""" def log_exception(self, exc_info): logger.exception('Exception happened during processing of request', exc_info=exc_info) def log_message(self, format, *args): logger.info(format, *args) def log_error(self, *args): logger.error(*args) class WSGIRequestHandlerLogger(WSGIRequestHandler): """WSGIRequestHandler that uses dulwich's logger for logging exceptions.""" def log_exception(self, exc_info): logger.exception('Exception happened during processing of request', exc_info=exc_info) def log_message(self, format, *args): logger.info(format, *args) def log_error(self, *args): logger.error(*args) def handle(self): """Handle a single HTTP request""" self.raw_requestline = self.rfile.readline() if not self.parse_request(): # An error code has been sent, just exit return handler = ServerHandlerLogger( self.rfile, self.wfile, self.get_stderr(), self.get_environ() ) handler.request_handler = self # backpointer for logging handler.run(self.server.get_app()) class WSGIServerLogger(WSGIServer): def handle_error(self, request, client_address): """Handle an error. """ logger.exception( 'Exception happened during processing of request from %s' % str(client_address)) def main(argv=sys.argv): """Entry point for starting an HTTP 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=8000, help="Port to listen on.") options, args = parser.parse_args(argv) if len(args) > 1: gitdir = args[1] else: gitdir = os.getcwd() log_utils.default_logging_config() backend = DictBackend({'/': Repo(gitdir)}) app = make_wsgi_chain(backend) server = make_server(options.listen_address, options.port, app, handler_class=WSGIRequestHandlerLogger, server_class=WSGIServerLogger) logger.info('Listening for HTTP connections on %s:%d', options.listen_address, options.port) server.serve_forever() if __name__ == '__main__': main()