diff --git a/dulwich/contrib/swift.py b/dulwich/contrib/swift.py index 2e792e4f..a106bb18 100644 --- a/dulwich/contrib/swift.py +++ b/dulwich/contrib/swift.py @@ -1,1052 +1,1052 @@ # 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 from io import BytesIO try: from ConfigParser import ConfigParser except ImportError: 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 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 :param path: The path to the configuration file :param 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 :param scon: a `SwiftConnector` instance :param filename: Path to the index file objectise :return: a `PackIndexer` instance """ f = scon.get_object(filename) try: return load_pack_index_file(filename, f) finally: f.close() def pack_info_create(pack_data, pack_index): pack = Pack.from_objects(pack_data, pack_index) info = {} for obj in pack.iterobjects(): # Commit if obj.type_num == Commit.type_num: info[obj.id] = (obj.type_num, obj.parents, obj.tree) # Tree elif obj.type_num == Tree.type_num: shas = [(s, n, not stat.S_ISDIR(m)) for n, m, s in obj.items() if not S_ISGITLINK(m)] info[obj.id] = (obj.type_num, shas) # Blob elif obj.type_num == Blob.type_num: info[obj.id] = None # Tag elif obj.type_num == Tag.type_num: info[obj.id] = (obj.type_num, obj.object[1]) return zlib.compress(json_dumps(info)) def load_pack_info(filename, scon=None, file=None): if not file: f = scon.get_object(filename) else: f = file if not f: return None try: return json_loads(zlib.decompress(f.read())) finally: f.close() class SwiftException(Exception): pass class SwiftConnector(object): """A Connector to swift that manage authentication and errors catching """ def __init__(self, root, conf): """ Initialize a SwiftConnector :param root: The swift container that will act as Git bare repository :param conf: A ConfigParser Object """ self.conf = conf self.auth_ver = self.conf.get("swift", "auth_ver") if self.auth_ver not in ["1", "2"]: raise NotImplementedError( "Wrong authentication version use either 1 or 2") self.auth_url = self.conf.get("swift", "auth_url") self.user = self.conf.get("swift", "username") self.password = self.conf.get("swift", "password") self.concurrency = self.conf.getint('swift', 'concurrency') or 10 self.http_timeout = self.conf.getint('swift', 'http_timeout') or 20 self.http_pool_length = \ self.conf.getint('swift', 'http_pool_length') or 10 self.region_name = self.conf.get("swift", "region_name") or "RegionOne" self.endpoint_type = \ self.conf.get("swift", "endpoint_type") or "internalURL" self.cache_length = self.conf.getint("swift", "cache_length") or 20 self.chunk_length = self.conf.getint("swift", "chunk_length") or 12228 self.root = root block_size = 1024 * 12 # 12KB if self.auth_ver == "1": self.storage_url, self.token = self.swift_auth_v1() else: self.storage_url, self.token = self.swift_auth_v2() token_header = {'X-Auth-Token': str(self.token)} self.httpclient = \ HTTPClient.from_url(str(self.storage_url), concurrency=self.http_pool_length, block_size=block_size, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, headers=token_header) self.base_path = str(posixpath.join( urlparse.urlparse(self.storage_url).path, self.root)) def swift_auth_v1(self): self.user = self.user.replace(";", ":") auth_httpclient = HTTPClient.from_url( self.auth_url, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, ) headers = {'X-Auth-User': self.user, 'X-Auth-Key': self.password} path = urlparse.urlparse(self.auth_url).path ret = auth_httpclient.request('GET', path, headers=headers) # Should do something with redirections (301 in my case) if ret.status_code < 200 or ret.status_code >= 300: raise SwiftException('AUTH v1.0 request failed on ' + '%s with error code %s (%s)' % (str(auth_httpclient.get_base_url()) + path, ret.status_code, str(ret.items()))) storage_url = ret['X-Storage-Url'] token = ret['X-Auth-Token'] return storage_url, token def swift_auth_v2(self): self.tenant, self.user = self.user.split(';') auth_dict = {} auth_dict['auth'] = {'passwordCredentials': { 'username': self.user, 'password': self.password, }, 'tenantName': self.tenant} auth_json = json_dumps(auth_dict) headers = {'Content-Type': 'application/json'} auth_httpclient = HTTPClient.from_url( self.auth_url, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, ) path = urlparse.urlparse(self.auth_url).path if not path.endswith('tokens'): path = posixpath.join(path, 'tokens') ret = auth_httpclient.request('POST', path, body=auth_json, headers=headers) if ret.status_code < 200 or ret.status_code >= 300: raise SwiftException('AUTH v2.0 request failed on ' + '%s with error code %s (%s)' % (str(auth_httpclient.get_base_url()) + path, ret.status_code, str(ret.items()))) auth_ret_json = json_loads(ret.read()) token = auth_ret_json['access']['token']['id'] catalogs = auth_ret_json['access']['serviceCatalog'] object_store = [o_store for o_store in catalogs if o_store['type'] == 'object-store'][0] endpoints = object_store['endpoints'] endpoint = [endp for endp in endpoints if endp["region"] == self.region_name][0] return endpoint[self.endpoint_type], token def test_root_exists(self): """Check that Swift container exist :return: 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 :raise: `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 :return: A list of dict that describe objects or None if container does not exist """ qs = '?format=json' path = self.base_path + qs ret = self.httpclient.request('GET', path) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('GET request failed with error code %s' % ret.status_code) content = ret.read() return json_loads(content) def get_object_stat(self, name): """Retrieve object stat :param name: The object name :return: 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 :param name: The object name :param content: A file object :raise: `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 :param name: The object name :param range: A string range like "0-10" to retrieve specified bytes in object content :return: 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 :param name: The object name :raise: `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 :raise: `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 :param scon: a `SwiftConnector` instance :param filename: the pack filename :param 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 - l = self.base_offset + 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" % (l, r)) + 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 :param length: amount of bytes to read :return: 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 :param 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 :return: 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 :param scon: a `SwiftConnector` instance :param 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. :param 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 @property def packs(self): """List with pack objects.""" if not self._pack_cache: self._update_pack_cache() return self._pack_cache.values() def _update_pack_cache(self): for pack in self._load_packs(): self._pack_cache[pack._basename] = pack 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. :return: 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 _load_packs(self): """Load all packs from Swift :return: a list of `SwiftPack` instances """ objects = self.scon.get_container_objects() pack_files = [o['name'].replace(".pack", "") for o in objects if o['name'].endswith(".pack")] return [SwiftPack(pack, scon=self.scon) for pack in pack_files] 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. :return: 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_known_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_known_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. :param root: The container which contains the bare repo :param 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. :return: True if permissions can be trusted, False otherwise. """ return False def _put_named_file(self, filename, contents): """Put an object in a Swift container :param filename: the path to the object to put on Swift :param contents: the content as bytestring """ f = BytesIO() f.write(contents) self.scon.put_object(filename, f) f.close() @classmethod def init_bare(cls, scon, conf): """Create a new bare repository. :param scon: a `SwiftConnector` instance :param conf: a ConfigParser object :return: 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.contrib.swift import load_conf from dulwich import log_utils logger = log_utils.getLogger(__name__) conf = load_conf(options.swift_config) backend = SwiftSystemBackend(logger, conf) log_utils.default_logging_config() server = TCPGitServer(backend, options.listen_address, port=options.port) server.serve_forever() def cmd_init(args): import optparse parser = optparse.OptionParser() parser.add_option("-c", "--swift_config", dest="swift_config", default="", help="Path to the configuration file for Swift backend.") options, args = parser.parse_args(args) conf = load_conf(options.swift_config) if args == []: parser.error("missing repository name") repo = args[0] scon = SwiftConnector(repo, conf) SwiftRepo.init_bare(scon, conf) def main(argv=sys.argv): commands = { "init": cmd_init, "daemon": cmd_daemon, } if len(sys.argv) < 2: print("Usage: %s <%s> [OPTIONS...]" % ( sys.argv[0], "|".join(commands.keys()))) sys.exit(1) cmd = sys.argv[1] if cmd not in commands: print("No such subcommand: %s" % cmd) sys.exit(1) commands[cmd](sys.argv[2:]) if __name__ == '__main__': main() diff --git a/dulwich/ignore.py b/dulwich/ignore.py index 089f2caa..df7277b0 100644 --- a/dulwich/ignore.py +++ b/dulwich/ignore.py @@ -1,358 +1,358 @@ # Copyright (C) 2017 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Parsing of gitignore files. For details for the matching rules, see https://git-scm.com/docs/gitignore """ import os.path import re import sys def _translate_segment(segment): if segment == b"*": return b'[^/]+' res = b"" i, n = 0, len(segment) while i < n: c = segment[i:i+1] i = i+1 if c == b'*': res += b'[^/]*' elif c == b'?': res += b'.' elif c == b'[': j = i if j < n and segment[j:j+1] == b'!': j = j+1 if j < n and segment[j:j+1] == b']': j = j+1 while j < n and segment[j:j+1] != b']': j = j+1 if j >= n: res += b'\\[' else: stuff = segment[i:j].replace(b'\\', b'\\\\') i = j+1 if stuff.startswith(b'!'): stuff = b'^' + stuff[1:] elif stuff.startswith(b'^'): stuff = b'\\' + stuff res += b'[' + stuff + b']' else: res += re.escape(c) return res def translate(pat): """Translate a shell PATTERN to a regular expression. There is no way to quote meta-characters. Originally copied from fnmatch in Python 2.7, but modified for Dulwich to cope with features in Git ignore patterns. """ res = b'(?ms)' if b'/' not in pat[:-1]: # If there's no slash, this is a filename-based match res += b'(.*/)?' if pat.startswith(b'**/'): # Leading **/ pat = pat[2:] res += b'(.*/)?' if pat.startswith(b'/'): pat = pat[1:] for i, segment in enumerate(pat.split(b'/')): if segment == b'**': res += b'(/.*)?' continue else: res += ((re.escape(b'/') if i > 0 else b'') + _translate_segment(segment)) if not pat.endswith(b'/'): res += b'/?' return res + b'\Z' def read_ignore_patterns(f): """Read a git ignore file. :param f: File-like object to read from :return: List of patterns """ - for l in f: - l = l.rstrip(b"\r\n") + for line in f: + line = line.rstrip(b"\r\n") # Ignore blank lines, they're used for readability. - if not l: + if not line: continue - if l.startswith(b'#'): + if line.startswith(b'#'): # Comment continue # Trailing spaces are ignored unless they are quoted with a backslash. - while l.endswith(b' ') and not l.endswith(b'\\ '): - l = l[:-1] - l = l.replace(b'\\ ', b' ') + while line.endswith(b' ') and not line.endswith(b'\\ '): + line = line[:-1] + line = line.replace(b'\\ ', b' ') - yield l + yield line def match_pattern(path, pattern, ignorecase=False): """Match a gitignore-style pattern against a path. :param path: Path to match :param pattern: Pattern to match :param ignorecase: Whether to do case-sensitive matching :return: bool indicating whether the pattern matched """ return Pattern(pattern, ignorecase).match(path) class Pattern(object): """A single ignore pattern.""" def __init__(self, pattern, ignorecase=False): self.pattern = pattern self.ignorecase = ignorecase if pattern[0:1] == b'!': self.is_exclude = False pattern = pattern[1:] else: if pattern[0:1] == b'\\': pattern = pattern[1:] self.is_exclude = True flags = 0 if self.ignorecase: flags = re.IGNORECASE self._re = re.compile(translate(pattern), flags) def __bytes__(self): return self.pattern def __str__(self): return self.pattern.decode(sys.getfilesystemencoding()) def __eq__(self, other): return (type(self) == type(other) and self.pattern == other.pattern and self.ignorecase == other.ignorecase) def __repr__(self): return "%s(%s, %r)" % ( type(self).__name__, self.pattern, self.ignorecase) def match(self, path): """Try to match a path against this ignore pattern. :param path: Path to match (relative to ignore location) :return: boolean """ return bool(self._re.match(path)) class IgnoreFilter(object): def __init__(self, patterns, ignorecase=False): self._patterns = [] self._ignorecase = ignorecase for pattern in patterns: self.append_pattern(pattern) def append_pattern(self, pattern): """Add a pattern to the set.""" self._patterns.append(Pattern(pattern, self._ignorecase)) def find_matching(self, path): """Yield all matching patterns for path. :param path: Path to match :return: Iterator over iterators """ if not isinstance(path, bytes): path = path.encode(sys.getfilesystemencoding()) for pattern in self._patterns: if pattern.match(path): yield pattern def is_ignored(self, path): """Check whether a path is ignored. For directories, include a trailing slash. :return: status is None if file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for pattern in self.find_matching(path): status = pattern.is_exclude return status @classmethod def from_path(cls, path, ignorecase=False): with open(path, 'rb') as f: ret = cls(read_ignore_patterns(f), ignorecase) ret._path = path return ret def __repr__(self): if getattr(self, '_path', None) is None: return "<%s>" % (type(self).__name__) else: return "%s.from_path(%r)" % (type(self).__name__, self._path) class IgnoreFilterStack(object): """Check for ignore status in multiple filters.""" def __init__(self, filters): self._filters = filters def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. :param path: Path to check :return: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for filter in self._filters: status = filter.is_ignored(path) if status is not None: return status return status def default_user_ignore_filter_path(config): """Return default user ignore filter path. :param config: A Config object :return: Path to a global ignore file """ try: return config.get(('core', ), 'excludesFile') except KeyError: pass xdg_config_home = os.environ.get( "XDG_CONFIG_HOME", os.path.expanduser("~/.config/"), ) return os.path.join(xdg_config_home, 'git', 'ignore') class IgnoreFilterManager(object): """Ignore file manager.""" def __init__(self, top_path, global_filters, ignorecase): self._path_filters = {} self._top_path = top_path self._global_filters = global_filters self._ignorecase = ignorecase def __repr__(self): return "%s(%s, %r, %r)" % ( type(self).__name__, self._top_path, self._global_filters, self._ignorecase) def _load_path(self, path): try: return self._path_filters[path] except KeyError: pass p = os.path.join(self._top_path, path, '.gitignore') try: self._path_filters[path] = IgnoreFilter.from_path( p, self._ignorecase) except IOError: self._path_filters[path] = None return self._path_filters[path] def find_matching(self, path): """Find matching patterns for path. Stops after the first ignore file with matches. :param path: Path to check :return: Iterator over Pattern instances """ if os.path.isabs(path): raise ValueError('%s is an absolute path' % path) filters = [(0, f) for f in self._global_filters] if os.path.sep != '/': path = path.replace(os.path.sep, '/') parts = path.split('/') for i in range(len(parts)+1): dirname = '/'.join(parts[:i]) for s, f in filters: relpath = '/'.join(parts[s:i]) if i < len(parts): # Paths leading up to the final part are all directories, # so need a trailing slash. relpath += '/' matches = list(f.find_matching(relpath)) if matches: return iter(matches) ignore_filter = self._load_path(dirname) if ignore_filter is not None: filters.insert(0, (i, ignore_filter)) return iter([]) def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. :param path: Path to check :return: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ matches = list(self.find_matching(path)) if matches: return matches[-1].is_exclude return None @classmethod def from_repo(cls, repo): """Create a IgnoreFilterManager from a repository. :param repo: Repository object :return: A `IgnoreFilterManager` object """ global_filters = [] for p in [ os.path.join(repo.controldir(), 'info', 'exclude'), default_user_ignore_filter_path(repo.get_config_stack())]: try: global_filters.append(IgnoreFilter.from_path(p)) except IOError: pass config = repo.get_config_stack() ignorecase = config.get_boolean((b'core'), (b'ignorecase'), False) return cls(repo.path, global_filters, ignorecase) diff --git a/dulwich/object_store.py b/dulwich/object_store.py index a73c6817..82ca1c20 100644 --- a/dulwich/object_store.py +++ b/dulwich/object_store.py @@ -1,1220 +1,1220 @@ # object_store.py -- Object store for git objects # Copyright (C) 2008-2013 Jelmer Vernooij # and others # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Git object store interfaces and implementation.""" from io import BytesIO import errno from itertools import chain import os import stat import sys import tempfile import time from dulwich.diff_tree import ( tree_changes, walk_trees, ) from dulwich.errors import ( NotTreeError, ) from dulwich.file import GitFile from dulwich.objects import ( Commit, ShaFile, Tag, Tree, ZERO_SHA, hex_to_sha, sha_to_hex, hex_to_filename, S_ISGITLINK, object_class, ) from dulwich.pack import ( Pack, PackData, PackInflater, iter_sha1, write_pack_header, write_pack_index_v2, write_pack_object, write_pack_objects, compute_file_sha, PackIndexer, PackStreamCopier, ) INFODIR = 'info' PACKDIR = 'pack' class BaseObjectStore(object): """Object store interface.""" def determine_wants_all(self, refs): return [sha for (ref, sha) in refs.items() if sha not in self and not ref.endswith(b"^{}") and not sha == ZERO_SHA] def iter_shas(self, shas): """Iterate over the objects for the specified shas. :param shas: Iterable object with SHAs :return: Object iterator """ return ObjectStoreIterator(self, shas) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" raise NotImplementedError(self.contains_loose) def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" raise NotImplementedError(self.contains_packed) def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ return self.contains_packed(sha) or self.contains_loose(sha) @property def packs(self): """Iterable of pack objects.""" raise NotImplementedError def get_raw(self, name): """Obtain the raw text for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ raise NotImplementedError(self.get_raw) def __getitem__(self, sha): """Obtain an object by SHA1.""" type_num, uncomp = self.get_raw(sha) return ShaFile.from_raw_string(type_num, uncomp, sha=sha) def __iter__(self): """Iterate over the SHAs that are present in this store.""" raise NotImplementedError(self.__iter__) def add_object(self, obj): """Add a single object to this object store. """ raise NotImplementedError(self.add_object) def add_objects(self, objects): """Add a set of objects to this object store. :param objects: Iterable over a list of (object, path) tuples """ raise NotImplementedError(self.add_objects) def tree_changes(self, source, target, want_unchanged=False): """Find the differences between the contents of two trees :param source: SHA1 of the source tree :param target: SHA1 of the target tree :param want_unchanged: Whether unchanged files should be reported :return: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ for change in tree_changes(self, source, target, want_unchanged=want_unchanged): yield ((change.old.path, change.new.path), (change.old.mode, change.new.mode), (change.old.sha, change.new.sha)) def iter_tree_contents(self, tree_id, include_trees=False): """Iterate the contents of a tree and all subtrees. Iteration is depth-first pre-order, as in e.g. os.walk. :param tree_id: SHA1 of the tree. :param include_trees: If True, include tree objects in the iteration. :return: Iterator over TreeEntry namedtuples for all the objects in a tree. """ for entry, _ in walk_trees(self, tree_id, None): if not stat.S_ISDIR(entry.mode) or include_trees: yield entry def find_missing_objects(self, haves, wants, progress=None, get_tagged=None, get_parents=lambda commit: commit.parents): """Find the missing objects required for a set of revisions. :param haves: Iterable over SHAs already in common. :param wants: Iterable over SHAs of objects to fetch. :param progress: Simple progress function that will be called with updated progress strings. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. :param get_parents: Optional function for getting the parents of a commit. :return: Iterator over (sha, path) pairs. """ finder = MissingObjectFinder(self, haves, wants, progress, get_tagged, get_parents=get_parents) return iter(finder.next, None) def find_common_revisions(self, graphwalker): """Find which revisions this store has in common using graphwalker. :param graphwalker: A graphwalker object. :return: List of SHAs that are in common """ haves = [] sha = next(graphwalker) while sha: if sha in self: haves.append(sha) graphwalker.ack(sha) sha = next(graphwalker) return haves def generate_pack_contents(self, have, want, progress=None): """Iterate over the contents of a pack file. :param have: List of SHA1s of objects that should not be sent :param want: List of SHA1s of objects that should be sent :param progress: Optional progress reporting method """ return self.iter_shas(self.find_missing_objects(have, want, progress)) def peel_sha(self, sha): """Peel all tags from a SHA. :param sha: The object SHA to peel. :return: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ obj = self[sha] obj_class = object_class(obj.type_name) while obj_class is Tag: obj_class, sha = obj.object obj = self[sha] return obj def _collect_ancestors(self, heads, common=set(), get_parents=lambda commit: commit.parents): """Collect all ancestors of heads up to (excluding) those in common. :param heads: commits to start from :param common: commits to end at, or empty set to walk repository completely :param get_parents: Optional function for getting the parents of a commit. :return: a tuple (A, B) where A - all commits reachable from heads but not present in common, B - common (shared) elements that are directly reachable from heads """ bases = set() commits = set() queue = [] queue.extend(heads) while queue: e = queue.pop(0) if e in common: bases.add(e) elif e not in commits: commits.add(e) cmt = self[e] queue.extend(get_parents(cmt)) return (commits, bases) def close(self): """Close any files opened by this object store.""" # Default implementation is a NO-OP class PackBasedObjectStore(BaseObjectStore): def __init__(self): self._pack_cache = {} @property def alternates(self): return [] def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed. This does not check alternates. """ for pack in self.packs: if sha in pack: return True return False def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ if self.contains_packed(sha) or self.contains_loose(sha): return True for alternate in self.alternates: if sha in alternate: return True return False def _pack_cache_stale(self): """Check whether the pack cache is stale.""" raise NotImplementedError(self._pack_cache_stale) def _add_known_pack(self, base_name, pack): """Add a newly appeared pack to the cache by path. """ prev_pack = self._pack_cache.get(base_name) if prev_pack is not pack: self._pack_cache[base_name] = pack if prev_pack: prev_pack.close() def _flush_pack_cache(self): pack_cache = self._pack_cache self._pack_cache = {} while pack_cache: (name, pack) = pack_cache.popitem() pack.close() def close(self): self._flush_pack_cache() @property def packs(self): """List with pack objects.""" if self._pack_cache is None or self._pack_cache_stale(): self._update_pack_cache() return self._pack_cache.values() def _iter_alternate_objects(self): """Iterate over the SHAs of all the objects in alternate stores.""" for alternate in self.alternates: for alternate_object in alternate: yield alternate_object def _iter_loose_objects(self): """Iterate over the SHAs of all loose objects.""" raise NotImplementedError(self._iter_loose_objects) def _get_loose_object(self, sha): raise NotImplementedError(self._get_loose_object) def _remove_loose_object(self, sha): raise NotImplementedError(self._remove_loose_object) def _remove_pack(self, name): raise NotImplementedError(self._remove_pack) def pack_loose_objects(self): """Pack loose objects. :return: Number of objects packed """ objects = set() for sha in self._iter_loose_objects(): objects.add((self._get_loose_object(sha), None)) self.add_objects(list(objects)) for obj, path in objects: self._remove_loose_object(obj.id) return len(objects) def repack(self): """Repack the packs in this repository. Note that this implementation is fairly naive and currently keeps all objects in memory while it repacks. """ loose_objects = set() for sha in self._iter_loose_objects(): loose_objects.add(self._get_loose_object(sha)) objects = {(obj, None) for obj in loose_objects} old_packs = {p.name(): p for p in self.packs} for name, pack in old_packs.items(): objects.update((obj, None) for obj in pack.iterobjects()) self._flush_pack_cache() # The name of the consolidated pack might match the name of a # pre-existing pack. Take care not to remove the newly created # consolidated pack. consolidated = self.add_objects(objects) old_packs.pop(consolidated.name(), None) for obj in loose_objects: self._remove_loose_object(obj.id) for name, pack in old_packs.items(): self._remove_pack(pack) self._update_pack_cache() return len(objects) def __iter__(self): """Iterate over the SHAs that are present in this store.""" iterables = (list(self.packs) + [self._iter_loose_objects()] + [self._iter_alternate_objects()]) return chain(*iterables) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose. This does not check alternates. """ return self._get_loose_object(sha) is not None def get_raw(self, name): """Obtain the raw text for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ if len(name) == 40: sha = hex_to_sha(name) hexsha = name elif len(name) == 20: sha = name hexsha = None else: raise AssertionError("Invalid object name %r" % name) for pack in self.packs: try: return pack.get_raw(sha) except KeyError: pass if hexsha is None: hexsha = sha_to_hex(name) ret = self._get_loose_object(hexsha) if ret is not None: return ret.type_num, ret.as_raw_string() for alternate in self.alternates: try: return alternate.get_raw(hexsha) except KeyError: pass raise KeyError(hexsha) def add_objects(self, objects): """Add a set of objects to this object store. :param objects: Iterable over (object, path) tuples, should support __len__. :return: Pack object of the objects written. """ if len(objects) == 0: # Don't bother writing an empty pack file return f, commit, abort = self.add_pack() try: write_pack_objects(f, objects) except: abort() raise else: return commit() class DiskObjectStore(PackBasedObjectStore): """Git-style object store that exists on disk.""" def __init__(self, path): """Open an object store. :param path: Path of the object store. """ super(DiskObjectStore, self).__init__() self.path = path self.pack_dir = os.path.join(self.path, PACKDIR) self._pack_cache_time = 0 self._pack_cache = {} self._alternates = None def __repr__(self): return "<%s(%r)>" % (self.__class__.__name__, self.path) @property def alternates(self): if self._alternates is not None: return self._alternates self._alternates = [] for path in self._read_alternate_paths(): self._alternates.append(DiskObjectStore(path)) return self._alternates def _read_alternate_paths(self): try: f = GitFile(os.path.join(self.path, INFODIR, "alternates"), 'rb') except (OSError, IOError) as e: if e.errno == errno.ENOENT: return raise with f: - for l in f.readlines(): - l = l.rstrip(b"\n") - if l[0] == b"#": + for line in f.readlines(): + line = line.rstrip(b"\n") + if line[0] == b"#": continue - if os.path.isabs(l): - yield l.decode(sys.getfilesystemencoding()) + if os.path.isabs(line): + yield line.decode(sys.getfilesystemencoding()) else: - yield os.path.join(self.path, l).decode( + yield os.path.join(self.path, line).decode( sys.getfilesystemencoding()) def add_alternate_path(self, path): """Add an alternate path to this object store. """ try: os.mkdir(os.path.join(self.path, INFODIR)) except OSError as e: if e.errno != errno.EEXIST: raise alternates_path = os.path.join(self.path, INFODIR, "alternates") with GitFile(alternates_path, 'wb') as f: try: orig_f = open(alternates_path, 'rb') except (OSError, IOError) as e: if e.errno != errno.ENOENT: raise else: with orig_f: f.write(orig_f.read()) f.write(path.encode(sys.getfilesystemencoding()) + b"\n") if not os.path.isabs(path): path = os.path.join(self.path, path) self.alternates.append(DiskObjectStore(path)) def _update_pack_cache(self): try: pack_dir_contents = os.listdir(self.pack_dir) except OSError as e: if e.errno == errno.ENOENT: self._pack_cache_time = 0 self.close() return raise self._pack_cache_time = max( os.stat(self.pack_dir).st_mtime, time.time()) pack_files = set() for name in pack_dir_contents: if name.startswith("pack-") and name.endswith(".pack"): # verify that idx exists first (otherwise the pack was not yet # fully written) idx_name = os.path.splitext(name)[0] + ".idx" if idx_name in pack_dir_contents: pack_name = name[:-len(".pack")] pack_files.add(pack_name) # Open newly appeared pack files for f in pack_files: if f not in self._pack_cache: self._pack_cache[f] = Pack(os.path.join(self.pack_dir, f)) # Remove disappeared pack files for f in set(self._pack_cache) - pack_files: self._pack_cache.pop(f).close() def _pack_cache_stale(self): try: return os.stat(self.pack_dir).st_mtime >= self._pack_cache_time except OSError as e: if e.errno == errno.ENOENT: return True raise def _get_shafile_path(self, sha): # Check from object dir return hex_to_filename(self.path, sha) def _iter_loose_objects(self): for base in os.listdir(self.path): if len(base) != 2: continue for rest in os.listdir(os.path.join(self.path, base)): yield (base+rest).encode(sys.getfilesystemencoding()) def _get_loose_object(self, sha): path = self._get_shafile_path(sha) try: return ShaFile.from_path(path) except (OSError, IOError) as e: if e.errno == errno.ENOENT: return None raise def _remove_loose_object(self, sha): os.remove(self._get_shafile_path(sha)) def _remove_pack(self, pack): os.remove(pack.data.path) os.remove(pack.index.path) def _get_pack_basepath(self, entries): suffix = iter_sha1(entry[0] for entry in entries) # TODO: Handle self.pack_dir being bytes suffix = suffix.decode('ascii') return os.path.join(self.pack_dir, "pack-" + suffix) def _complete_thin_pack(self, f, path, copier, indexer): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param f: Open file object for the pack. :param path: Path to the pack file. :param copier: A PackStreamCopier to use for writing pack data. :param indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Must flush before reading (http://bugs.python.org/issue3207) f.flush() # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Must reposition before writing (http://bugs.python.org/issue3207) f.seek(0, os.SEEK_CUR) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) offset = f.tell() crc32 = write_pack_object(f, type_num, data, sha=new_sha) entries.append((ext_sha, offset, crc32)) pack_sha = new_sha.digest() f.write(pack_sha) f.close() # Move the pack in. entries.sort() pack_base_name = self._get_pack_basepath(entries) if sys.platform == 'win32': try: os.rename(path, pack_base_name + '.pack') except WindowsError: os.remove(pack_base_name + '.pack') os.rename(path, pack_base_name + '.pack') else: os.rename(path, pack_base_name + '.pack') # Write the index. index_file = GitFile(pack_base_name + '.idx', 'wb') try: write_pack_index_v2(index_file, entries, pack_sha) index_file.close() finally: index_file.abort() # Add the pack to the store and return it. final_pack = Pack(pack_base_name) final_pack.check_length_and_checksum() self._add_known_pack(pack_base_name, final_pack) return final_pack def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. They should never be placed in the object store directly, and always indexed and completed as they are copied. :param read_all: Read function that blocks until the number of requested bytes are read. :param read_some: Read function that returns at least one byte, but may not return the number of bytes requested. :return: A Pack object pointing at the now-completed thin pack in the objects/pack directory. """ fd, path = tempfile.mkstemp(dir=self.path, prefix='tmp_pack_') with os.fdopen(fd, 'w+b') as f: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() return self._complete_thin_pack(f, path, copier, indexer) def move_in_pack(self, path): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param path: Path to the pack file. """ with PackData(path) as p: entries = p.sorted_entries() basename = self._get_pack_basepath(entries) with GitFile(basename+".idx", "wb") as f: write_pack_index_v2(f, entries, p.get_stored_checksum()) os.rename(path, basename + ".pack") final_pack = Pack(basename) self._add_known_pack(basename, final_pack) return final_pack def add_pack(self): """Add a new pack to this object store. :return: Fileobject to write to, a commit function to call when the pack is finished and an abort function. """ fd, path = tempfile.mkstemp(dir=self.pack_dir, suffix=".pack") f = os.fdopen(fd, 'wb') def commit(): f.flush() os.fsync(fd) f.close() if os.path.getsize(path) > 0: return self.move_in_pack(path) else: os.remove(path) return None def abort(): f.close() os.remove(path) return f, commit, abort def add_object(self, obj): """Add a single object to this object store. :param obj: Object to add """ path = self._get_shafile_path(obj.id) dir = os.path.dirname(path) try: os.mkdir(dir) except OSError as e: if e.errno != errno.EEXIST: raise if os.path.exists(path): return # Already there, no need to write again with GitFile(path, 'wb') as f: f.write(obj.as_legacy_object()) @classmethod def init(cls, path): try: os.mkdir(path) except OSError as e: if e.errno != errno.EEXIST: raise os.mkdir(os.path.join(path, "info")) os.mkdir(os.path.join(path, PACKDIR)) return cls(path) class MemoryObjectStore(BaseObjectStore): """Object store that keeps all objects in memory.""" def __init__(self): super(MemoryObjectStore, self).__init__() self._data = {} def _to_hexsha(self, sha): if len(sha) == 40: return sha elif len(sha) == 20: return sha_to_hex(sha) else: raise ValueError("Invalid sha %r" % (sha,)) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" return self._to_hexsha(sha) in self._data def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" return False def __iter__(self): """Iterate over the SHAs that are present in this store.""" return iter(self._data.keys()) @property def packs(self): """List with pack objects.""" return [] def get_raw(self, name): """Obtain the raw text for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ obj = self[self._to_hexsha(name)] return obj.type_num, obj.as_raw_string() def __getitem__(self, name): return self._data[self._to_hexsha(name)].copy() def __delitem__(self, name): """Delete an object from this store, for testing only.""" del self._data[self._to_hexsha(name)] def add_object(self, obj): """Add a single object to this object store. """ self._data[obj.id] = obj.copy() def add_objects(self, objects): """Add a set of objects to this object store. :param objects: Iterable over a list of (object, path) tuples """ for obj, path in objects: self.add_object(obj) def add_pack(self): """Add a new pack to this object store. Because this object store doesn't support packs, we extract and add the individual objects. :return: Fileobject to write to and a commit function to call when the pack is finished. """ f = BytesIO() def commit(): p = PackData.from_file(BytesIO(f.getvalue()), f.tell()) f.close() for obj in PackInflater.for_pack_data(p, self.get_raw): self.add_object(obj) def abort(): pass return f, commit, abort def _complete_thin_pack(self, f, indexer): """Complete a thin pack by adding external references. :param f: Open file object for the pack. :param indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) write_pack_object(f, type_num, data, sha=new_sha) pack_sha = new_sha.digest() f.write(pack_sha) def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. Because this object store doesn't support packs, we extract and add the individual objects. :param read_all: Read function that blocks until the number of requested bytes are read. :param read_some: Read function that returns at least one byte, but may not return the number of bytes requested. """ f, commit, abort = self.add_pack() try: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() self._complete_thin_pack(f, indexer) except: abort() raise else: commit() class ObjectImporter(object): """Interface for importing objects.""" def __init__(self, count): """Create a new ObjectImporter. :param count: Number of objects that's going to be imported. """ self.count = count def add_object(self, object): """Add an object.""" raise NotImplementedError(self.add_object) def finish(self, object): """Finish the import and write objects to disk.""" raise NotImplementedError(self.finish) class ObjectIterator(object): """Interface for iterating over objects.""" def iterobjects(self): raise NotImplementedError(self.iterobjects) class ObjectStoreIterator(ObjectIterator): """ObjectIterator that works on top of an ObjectStore.""" def __init__(self, store, sha_iter): """Create a new ObjectIterator. :param store: Object store to retrieve from :param sha_iter: Iterator over (sha, path) tuples """ self.store = store self.sha_iter = sha_iter self._shas = [] def __iter__(self): """Yield tuple with next object and path.""" for sha, path in self.itershas(): yield self.store[sha], path def iterobjects(self): """Iterate over just the objects.""" for o, path in self: yield o def itershas(self): """Iterate over the SHAs.""" for sha in self._shas: yield sha for sha in self.sha_iter: self._shas.append(sha) yield sha def __contains__(self, needle): """Check if an object is present. :note: This checks if the object is present in the underlying object store, not if it would be yielded by the iterator. :param needle: SHA1 of the object to check for """ return needle in self.store def __getitem__(self, key): """Find an object by SHA1. :note: This retrieves the object from the underlying object store. It will also succeed if the object would not be returned by the iterator. """ return self.store[key] def __len__(self): """Return the number of objects.""" return len(list(self.itershas())) def tree_lookup_path(lookup_obj, root_sha, path): """Look up an object in a Git tree. :param lookup_obj: Callback for retrieving object by SHA1 :param root_sha: SHA1 of the root tree :param path: Path to lookup :return: A tuple of (mode, SHA) of the resulting path. """ tree = lookup_obj(root_sha) if not isinstance(tree, Tree): raise NotTreeError(root_sha) return tree.lookup_path(lookup_obj, path) def _collect_filetree_revs(obj_store, tree_sha, kset): """Collect SHA1s of files and directories for specified tree. :param obj_store: Object store to get objects by SHA from :param tree_sha: tree reference to walk :param kset: set to fill with references to files and directories """ filetree = obj_store[tree_sha] for name, mode, sha in filetree.iteritems(): if not S_ISGITLINK(mode) and sha not in kset: kset.add(sha) if stat.S_ISDIR(mode): _collect_filetree_revs(obj_store, sha, kset) def _split_commits_and_tags(obj_store, lst, ignore_unknown=False): """Split object id list into three lists with commit, tag, and other SHAs. Commits referenced by tags are included into commits list as well. Only SHA1s known in this repository will get through, and unless ignore_unknown argument is True, KeyError is thrown for SHA1 missing in the repository :param obj_store: Object store to get objects by SHA1 from :param lst: Collection of commit and tag SHAs :param ignore_unknown: True to skip SHA1 missing in the repository silently. :return: A tuple of (commits, tags, others) SHA1s """ commits = set() tags = set() others = set() for e in lst: try: o = obj_store[e] except KeyError: if not ignore_unknown: raise else: if isinstance(o, Commit): commits.add(e) elif isinstance(o, Tag): tags.add(e) tagged = o.object[1] c, t, o = _split_commits_and_tags( obj_store, [tagged], ignore_unknown=ignore_unknown) commits |= c tags |= t others |= o else: others.add(e) return (commits, tags, others) class MissingObjectFinder(object): """Find the objects missing from another object store. :param object_store: Object store containing at least all objects to be sent :param haves: SHA1s of commits not to send (already present in target) :param wants: SHA1s of commits to send :param progress: Optional function to report progress to. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. :param get_parents: Optional function for getting the parents of a commit. :param tagged: dict of pointed-to sha -> tag sha for including tags """ def __init__(self, object_store, haves, wants, progress=None, get_tagged=None, get_parents=lambda commit: commit.parents): self.object_store = object_store self._get_parents = get_parents # process Commits and Tags differently # Note, while haves may list commits/tags not available locally, # and such SHAs would get filtered out by _split_commits_and_tags, # wants shall list only known SHAs, and otherwise # _split_commits_and_tags fails with KeyError have_commits, have_tags, have_others = ( _split_commits_and_tags(object_store, haves, True)) want_commits, want_tags, want_others = ( _split_commits_and_tags(object_store, wants, False)) # all_ancestors is a set of commits that shall not be sent # (complete repository up to 'haves') all_ancestors = object_store._collect_ancestors( have_commits, get_parents=self._get_parents)[0] # all_missing - complete set of commits between haves and wants # common - commits from all_ancestors we hit into while # traversing parent hierarchy of wants missing_commits, common_commits = object_store._collect_ancestors( want_commits, all_ancestors, get_parents=self._get_parents) self.sha_done = set() # Now, fill sha_done with commits and revisions of # files and directories known to be both locally # and on target. Thus these commits and files # won't get selected for fetch for h in common_commits: self.sha_done.add(h) cmt = object_store[h] _collect_filetree_revs(object_store, cmt.tree, self.sha_done) # record tags we have as visited, too for t in have_tags: self.sha_done.add(t) missing_tags = want_tags.difference(have_tags) missing_others = want_others.difference(have_others) # in fact, what we 'want' is commits, tags, and others # we've found missing wants = missing_commits.union(missing_tags) wants = wants.union(missing_others) self.objects_to_send = set([(w, None, False) for w in wants]) if progress is None: self.progress = lambda x: None else: self.progress = progress self._tagged = get_tagged and get_tagged() or {} def add_todo(self, entries): self.objects_to_send.update([e for e in entries if not e[0] in self.sha_done]) def next(self): while True: if not self.objects_to_send: return None (sha, name, leaf) = self.objects_to_send.pop() if sha not in self.sha_done: break if not leaf: o = self.object_store[sha] if isinstance(o, Commit): self.add_todo([(o.tree, "", False)]) elif isinstance(o, Tree): self.add_todo([(s, n, not stat.S_ISDIR(m)) for n, m, s in o.iteritems() if not S_ISGITLINK(m)]) elif isinstance(o, Tag): self.add_todo([(o.object[1], None, False)]) if sha in self._tagged: self.add_todo([(self._tagged[sha], None, True)]) self.sha_done.add(sha) self.progress(("counting objects: %d\r" % len(self.sha_done)).encode('ascii')) return (sha, name) __next__ = next class ObjectStoreGraphWalker(object): """Graph walker that finds what commits are missing from an object store. :ivar heads: Revisions without descendants in the local repo :ivar get_parents: Function to retrieve parents in the local repo """ def __init__(self, local_heads, get_parents): """Create a new instance. :param local_heads: Heads to start search with :param get_parents: Function for finding the parents of a SHA1. """ self.heads = set(local_heads) self.get_parents = get_parents self.parents = {} def ack(self, sha): """Ack that a revision and its ancestors are present in the source.""" if len(sha) != 40: raise ValueError("unexpected sha %r received" % sha) ancestors = set([sha]) # stop if we run out of heads to remove while self.heads: for a in ancestors: if a in self.heads: self.heads.remove(a) # collect all ancestors new_ancestors = set() for a in ancestors: ps = self.parents.get(a) if ps is not None: new_ancestors.update(ps) self.parents[a] = None # no more ancestors; stop if not new_ancestors: break ancestors = new_ancestors def next(self): """Iterate over ancestors of heads in the target.""" if self.heads: ret = self.heads.pop() ps = self.get_parents(ret) self.parents[ret] = ps self.heads.update( [p for p in ps if p not in self.parents]) return ret return None __next__ = next def commit_tree_changes(object_store, tree, changes): """Commit a specified set of changes to a tree structure. This will apply a set of changes on top of an existing tree, storing new objects in object_store. changes are a list of tuples with (path, mode, object_sha). Paths can be both blobs and trees. See the mode and object sha to None deletes the path. This method works especially well if there are only a small number of changes to a big tree. For a large number of changes to a large tree, use e.g. commit_tree. :param object_store: Object store to store new objects in and retrieve old ones from. :param tree: Original tree root :param changes: changes to apply :return: New tree root object """ # TODO(jelmer): Save up the objects and add them using .add_objects # rather than with individual calls to .add_object. nested_changes = {} for (path, new_mode, new_sha) in changes: try: (dirname, subpath) = path.split(b'/', 1) except ValueError: if new_sha is None: del tree[path] else: tree[path] = (new_mode, new_sha) else: nested_changes.setdefault(dirname, []).append( (subpath, new_mode, new_sha)) for name, subchanges in nested_changes.items(): try: orig_subtree = object_store[tree[name][1]] except KeyError: orig_subtree = Tree() subtree = commit_tree_changes(object_store, orig_subtree, subchanges) if len(subtree) == 0: del tree[name] else: tree[name] = (stat.S_IFDIR, subtree.id) object_store.add_object(tree) return tree diff --git a/dulwich/objects.py b/dulwich/objects.py index e659e41f..03f44026 100644 --- a/dulwich/objects.py +++ b/dulwich/objects.py @@ -1,1336 +1,1336 @@ # 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, ) 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 def S_ISGITLINK(m): """Check if a mode indicates a submodule. :param m: Mode to check :return: 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. :param type: Either a type name string or a numeric type. :return: 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. :param hex: Hex string to check :param error_msg: Error message to use in exception :raise 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. :param identity: Identity string :param 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 git_line(*items): """Formats items into a space sepreated 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) size = int(size) # sanity check 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): """Return chunks representing the object in the experimental format. :return: List of strings """ compobj = zlib.compressobj() yield compobj.compress(self._header()) for chunk in self.as_raw_chunks(): yield compobj.compress(chunk) yield compobj.flush() def as_legacy_object(self): """Return string representing the object in the experimental format. """ return b''.join(self.as_legacy_object_chunks()) def as_raw_chunks(self): """Return chunks with serialization of the object. :return: 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. :return: String object """ return b''.join(self.as_raw_chunks()) def __str__(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 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. :param type_num: The numeric type of the object. :param string: The raw uncompressed contents. :param 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. :param type_num: The numeric type of the object. :param chunks: An iterable of the raw uncompressed contents. :param 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. :param member: the member variable to check for :param error_msg: the message for an error if the member is missing :raise 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. :raise ObjectFormatException: if the object is malformed in some way :raise 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): return not isinstance(other, ShaFile) or self.id != other.id def __eq__(self, other): """Return True if the SHAs of the two objects match. It doesn't make sense to talk about an order on ShaFiles, so we don't override the rich comparison methods (__le__, etc.). """ return isinstance(other, ShaFile) and self.id == other.id def __lt__(self, other): if not isinstance(other, ShaFile): raise TypeError return self.id < other.id def __le__(self, other): if not isinstance(other, ShaFile): raise TypeError return self.id <= other.id def __cmp__(self, other): 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.") 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).") @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. :raise 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. :param chunks: the raw chunks of the tag or commit object. :return: 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 l in f: - if l.startswith(b' '): + for line in f: + if line.startswith(b' '): # Indented continuation of the previous line - v += l[1:] + v += line[1:] else: if k is not None: # We parsed a new header, return its value yield (k, _strip_last_newline(v)) - if l == b'\n': + if line == b'\n': # Empty line indicates end of headers break - (k, v) = l.split(b' ', 1) + (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') def __init__(self): super(Tag, self).__init__() self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False @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. :raise 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") 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) 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: try: sep = value.index(b'> ') except ValueError: self._tagger = value self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False else: self._tagger = value[0:sep+1] try: (timetext, timezonetext) = ( value[sep+2:].rsplit(b' ', 1)) self._tag_time = int(timetext) self._tag_timezone, self._tag_timezone_neg_utc = ( parse_timezone(timezonetext)) except ValueError as e: raise ObjectFormatException(e) elif field is None: self._message = value else: raise ObjectFormatException("Unknown field %s" % field) def _get_object(self): """Get the object pointed to by this tag. :return: 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") 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. :param text: Serialized text to parse :return: iterator of tuples of (name, mode, sha) :raise ObjectFormatException: if the object was malformed in some way """ count = 0 l = len(text) while count < l: 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. :param items: Sorted iterable over (name, mode, sha) tuples :return: 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. :param 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. :param entries: Dictionary mapping names to (mode, sha) tuples :return: 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. :param 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. :param name: Name of the directory entry :param mode: Mode of entry :param hexsha: Hexsha of the referenced object :return: 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. :param name: The name of the entry, as a string. :param 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. :param mode: The mode of the entry as an integral type. Not all possible modes are supported by git; see check() for details. :param name: The name of the entry, as a string. :param 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. :param name_order: If True, iterate in name order instead of tree order. :return: Iterator over (name, mode, sha) tuples """ return sorted_tree_items(self._entries, name_order) def items(self): """Return the sorted entries in this tree. :return: 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. :raise 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'..'): raise ObjectFormatException('invalid name %s' % name) 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. :param lookup_obj: Callback for retrieving object by SHA1 :param path: Path to lookup :return: 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'). :param text: Text to parse. :return: 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. :param offset: Timezone offset as seconds difference to UTC :param 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_commit(chunks): """Parse a commit object from chunks. :param chunks: Chunks to parse :return: 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, timetext, timezonetext = value.rsplit(b' ', 2) author_time = int(timetext) author_info = (author, author_time, parse_timezone(timezonetext)) elif field == _COMMITTER_HEADER: committer, timetext, timezonetext = value.rsplit(b' ', 2) commit_time = int(timetext) commit_info = ( committer, commit_time, parse_timezone(timezonetext)) 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. :raise 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") # times are currently checked when set 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") 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/patch.py b/dulwich/patch.py index 24b06154..b162c761 100644 --- a/dulwich/patch.py +++ b/dulwich/patch.py @@ -1,349 +1,349 @@ # patch.py -- For dealing with packed-style patches. # Copyright (C) 2009-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Classes for dealing with git am-style patches. These patches are basically unified diffs with some extra metadata tacked on. """ from difflib import SequenceMatcher import email.parser import time from dulwich.objects import ( Blob, Commit, S_ISGITLINK, ) FIRST_FEW_BYTES = 8000 def write_commit_patch(f, commit, contents, progress, version=None, encoding=None): """Write a individual file patch. :param commit: Commit object :param progress: Tuple with current patch number and total. :return: tuple with filename and contents """ encoding = encoding or getattr(f, "encoding", "ascii") if isinstance(contents, str): contents = contents.encode(encoding) (num, total) = progress f.write(b"From " + commit.id + b" " + time.ctime(commit.commit_time).encode(encoding) + b"\n") f.write(b"From: " + commit.author + b"\n") f.write(b"Date: " + time.strftime("%a, %d %b %Y %H:%M:%S %Z").encode(encoding) + b"\n") f.write(("Subject: [PATCH %d/%d] " % (num, total)).encode(encoding) + commit.message + b"\n") f.write(b"\n") f.write(b"---\n") try: import subprocess p = subprocess.Popen(["diffstat"], stdout=subprocess.PIPE, stdin=subprocess.PIPE) except (ImportError, OSError): pass # diffstat not available? else: (diffstat, _) = p.communicate(contents) f.write(diffstat) f.write(b"\n") f.write(contents) f.write(b"-- \n") if version is None: from dulwich import __version__ as dulwich_version f.write(b"Dulwich %d.%d.%d\n" % dulwich_version) else: f.write(version.encode(encoding) + b"\n") def get_summary(commit): """Determine the summary line for use in a filename. :param commit: Commit :return: Summary string """ return commit.message.splitlines()[0].replace(" ", "-") # Unified Diff def _format_range_unified(start, stop): 'Convert range to the "ed" format' # Per the diff spec at http://www.unix.org/single_unix_specification/ beginning = start + 1 # lines start numbering with one length = stop - start if length == 1: return '{}'.format(beginning) if not length: beginning -= 1 # empty ranges begin at line just before the range return '{},{}'.format(beginning, length) def unified_diff(a, b, fromfile='', tofile='', fromfiledate='', tofiledate='', n=3, lineterm='\n'): """difflib.unified_diff that can detect "No newline at end of file" as original "git diff" does. Based on the same function in Python2.7 difflib.py """ started = False for group in SequenceMatcher(None, a, b).get_grouped_opcodes(n): if not started: started = True fromdate = '\t{}'.format(fromfiledate) if fromfiledate else '' todate = '\t{}'.format(tofiledate) if tofiledate else '' yield '--- {}{}{}'.format( fromfile.decode("ascii"), fromdate, lineterm ).encode('ascii') yield '+++ {}{}{}'.format( tofile.decode("ascii"), todate, lineterm ).encode('ascii') first, last = group[0], group[-1] file1_range = _format_range_unified(first[1], last[2]) file2_range = _format_range_unified(first[3], last[4]) yield '@@ -{} +{} @@{}'.format( file1_range, file2_range, lineterm ).encode('ascii') for tag, i1, i2, j1, j2 in group: if tag == 'equal': for line in a[i1:i2]: yield b' ' + line continue if tag in ('replace', 'delete'): for line in a[i1:i2]: if not line[-1:] == b'\n': line += b'\n\\ No newline at end of file\n' yield b'-' + line if tag in ('replace', 'insert'): for line in b[j1:j2]: if not line[-1:] == b'\n': line += b'\n\\ No newline at end of file\n' yield b'+' + line def is_binary(content): """See if the first few bytes contain any null characters. :param content: Bytestring to check for binary content """ return b'\0' in content[:FIRST_FEW_BYTES] def shortid(hexsha): if hexsha is None: return b"0" * 7 else: return hexsha[:7] def patch_filename(p, root): if p is None: return b"/dev/null" else: return root + b"/" + p def write_object_diff(f, store, old_file, new_file, diff_binary=False): """Write the diff for an object. :param f: File-like object to write to :param store: Store to retrieve objects from, if necessary :param old_file: (path, mode, hexsha) tuple :param new_file: (path, mode, hexsha) tuple :param diff_binary: Whether to diff files even if they are considered binary files by is_binary(). :note: the tuple elements should be None for nonexistant files """ (old_path, old_mode, old_id) = old_file (new_path, new_mode, new_id) = new_file old_path = patch_filename(old_path, b"a") new_path = patch_filename(new_path, b"b") def content(mode, hexsha): if hexsha is None: return Blob.from_string(b'') elif S_ISGITLINK(mode): return Blob.from_string(b"Submodule commit " + hexsha + b"\n") else: return store[hexsha] def lines(content): if not content: return [] else: return content.splitlines() f.writelines(gen_diff_header( (old_path, new_path), (old_mode, new_mode), (old_id, new_id))) old_content = content(old_mode, old_id) new_content = content(new_mode, new_id) if not diff_binary and ( is_binary(old_content.data) or is_binary(new_content.data)): f.write(b"Binary files " + old_path + b" and " + new_path + b" differ\n") else: f.writelines(unified_diff(lines(old_content), lines(new_content), old_path, new_path)) # TODO(jelmer): Support writing unicode, rather than bytes. def gen_diff_header(paths, modes, shas): """Write a blob diff header. :param paths: Tuple with old and new path :param modes: Tuple with old and new modes :param shas: Tuple with old and new shas """ (old_path, new_path) = paths (old_mode, new_mode) = modes (old_sha, new_sha) = shas yield b"diff --git " + old_path + b" " + new_path + b"\n" if old_mode != new_mode: if new_mode is not None: if old_mode is not None: yield ("old mode %o\n" % old_mode).encode('ascii') yield ("new mode %o\n" % new_mode).encode('ascii') else: yield ("deleted mode %o\n" % old_mode).encode('ascii') yield b"index " + shortid(old_sha) + b".." + shortid(new_sha) if new_mode is not None: yield (" %o" % new_mode).encode('ascii') yield b"\n" # TODO(jelmer): Support writing unicode, rather than bytes. def write_blob_diff(f, old_file, new_file): """Write blob diff. :param f: File-like object to write to :param old_file: (path, mode, hexsha) tuple (None if nonexisting) :param new_file: (path, mode, hexsha) tuple (None if nonexisting) :note: The use of write_object_diff is recommended over this function. """ (old_path, old_mode, old_blob) = old_file (new_path, new_mode, new_blob) = new_file old_path = patch_filename(old_path, b"a") new_path = patch_filename(new_path, b"b") def lines(blob): if blob is not None: return blob.splitlines() else: return [] f.writelines(gen_diff_header( (old_path, new_path), (old_mode, new_mode), (getattr(old_blob, "id", None), getattr(new_blob, "id", None)))) old_contents = lines(old_blob) new_contents = lines(new_blob) f.writelines(unified_diff(old_contents, new_contents, old_path, new_path)) def write_tree_diff(f, store, old_tree, new_tree, diff_binary=False): """Write tree diff. :param f: File-like object to write to. :param old_tree: Old tree id :param new_tree: New tree id :param diff_binary: Whether to diff files even if they are considered binary files by is_binary(). """ changes = store.tree_changes(old_tree, new_tree) for (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) in changes: write_object_diff(f, store, (oldpath, oldmode, oldsha), (newpath, newmode, newsha), diff_binary=diff_binary) def git_am_patch_split(f, encoding=None): """Parse a git-am-style patch and split it up into bits. :param f: File-like object to parse :param encoding: Encoding to use when creating Git objects :return: Tuple with commit object, diff contents and git version """ encoding = encoding or getattr(f, "encoding", "ascii") contents = f.read() if (isinstance(contents, bytes) and getattr(email.parser, "BytesParser", None)): parser = email.parser.BytesParser() msg = parser.parsebytes(contents) else: parser = email.parser.Parser() msg = parser.parsestr(contents) return parse_patch_message(msg, encoding) def parse_patch_message(msg, encoding=None): """Extract a Commit object and patch from an e-mail message. :param msg: An email message (email.message.Message) :param encoding: Encoding to use to encode Git commits :return: Tuple with commit object, diff contents and git version """ c = Commit() c.author = msg["from"].encode(encoding) c.committer = msg["from"].encode(encoding) try: patch_tag_start = msg["subject"].index("[PATCH") except ValueError: subject = msg["subject"] else: close = msg["subject"].index("] ", patch_tag_start) subject = msg["subject"][close+2:] c.message = (subject.replace("\n", "") + "\n").encode(encoding) first = True body = msg.get_payload(decode=True) lines = body.splitlines(True) line_iter = iter(lines) - for l in line_iter: - if l == b"---\n": + for line in line_iter: + if line == b"---\n": break if first: - if l.startswith(b"From: "): - c.author = l[len(b"From: "):].rstrip() + if line.startswith(b"From: "): + c.author = line[len(b"From: "):].rstrip() else: - c.message += b"\n" + l + c.message += b"\n" + line first = False else: - c.message += l + c.message += line diff = b"" - for l in line_iter: - if l == b"-- \n": + for line in line_iter: + if line == b"-- \n": break - diff += l + diff += line try: version = next(line_iter).rstrip(b"\n") except StopIteration: version = None return c, diff, version diff --git a/dulwich/refs.py b/dulwich/refs.py index 0a19a16c..ba00a8a2 100644 --- a/dulwich/refs.py +++ b/dulwich/refs.py @@ -1,821 +1,821 @@ # refs.py -- For dealing with git refs # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Ref handling. """ import errno import os import sys from dulwich.errors import ( PackedRefsException, RefFormatError, ) from dulwich.objects import ( git_line, valid_hexsha, ZERO_SHA, ) from dulwich.file import ( GitFile, ensure_dir_exists, ) SYMREF = b'ref: ' LOCAL_BRANCH_PREFIX = b'refs/heads/' BAD_REF_CHARS = set(b'\177 ~^:?*[') ANNOTATED_TAG_SUFFIX = b'^{}' def parse_symref_value(contents): """Parse a symref value. :param contents: Contents to parse :return: Destination """ if contents.startswith(SYMREF): return contents[len(SYMREF):].rstrip(b'\r\n') raise ValueError(contents) def check_ref_format(refname): """Check if a refname is correctly formatted. Implements all the same rules as git-check-ref-format[1]. [1] http://www.kernel.org/pub/software/scm/git/docs/git-check-ref-format.html :param refname: The refname to check :return: True if refname is valid, False otherwise """ # These could be combined into one big expression, but are listed # separately to parallel [1]. if b'/.' in refname or refname.startswith(b'.'): return False if b'/' not in refname: return False if b'..' in refname: return False for i, c in enumerate(refname): if ord(refname[i:i+1]) < 0o40 or c in BAD_REF_CHARS: return False if refname[-1] in b'/.': return False if refname.endswith(b'.lock'): return False if b'@{' in refname: return False if b'\\' in refname: return False return True class RefsContainer(object): """A container for refs.""" def set_symbolic_ref(self, name, other): """Make a ref point at another ref. :param name: Name of the ref to set :param other: Name of the ref to point at """ raise NotImplementedError(self.set_symbolic_ref) def get_packed_refs(self): """Get contents of the packed-refs file. :return: Dictionary mapping ref names to SHA1s :note: Will return an empty dictionary when no packed-refs file is present. """ raise NotImplementedError(self.get_packed_refs) def get_peeled(self, name): """Return the cached peeled value of a ref, if available. :param name: Name of the ref to peel :return: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If the ref may point to a tag, but no cached information is available, None is returned. """ return None def import_refs(self, base, other): for name, value in other.items(): self[b'/'.join((base, name))] = value def allkeys(self): """All refs present in this container.""" raise NotImplementedError(self.allkeys) def keys(self, base=None): """Refs present in this container. :param base: An optional base to return refs under. :return: An unsorted set of valid refs in this container, including packed refs. """ if base is not None: return self.subkeys(base) else: return self.allkeys() def subkeys(self, base): """Refs present in this container under a base. :param base: The base to return refs under. :return: A set of valid refs in this container under the base; the base prefix is stripped from the ref names returned. """ keys = set() base_len = len(base) + 1 for refname in self.allkeys(): if refname.startswith(base): keys.add(refname[base_len:]) return keys def as_dict(self, base=None): """Return the contents of this container as a dictionary. """ ret = {} keys = self.keys(base) if base is None: base = b'' else: base = base.rstrip(b'/') for key in keys: try: ret[key] = self[(base + b'/' + key).strip(b'/')] except KeyError: continue # Unable to resolve return ret def _check_refname(self, name): """Ensure a refname is valid and lives in refs or is HEAD. HEAD is not a valid refname according to git-check-ref-format, but this class needs to be able to touch HEAD. Also, check_ref_format expects refnames without the leading 'refs/', but this class requires that so it cannot touch anything outside the refs dir (or HEAD). :param name: The name of the reference. :raises KeyError: if a refname is not HEAD or is otherwise not valid. """ if name in (b'HEAD', b'refs/stash'): return if not name.startswith(b'refs/') or not check_ref_format(name[5:]): raise RefFormatError(name) def read_ref(self, refname): """Read a reference without following any references. :param refname: The name of the reference :return: The contents of the ref file, or None if it does not exist. """ contents = self.read_loose_ref(refname) if not contents: contents = self.get_packed_refs().get(refname, None) return contents def read_loose_ref(self, name): """Read a loose reference and return its contents. :param name: the refname to read :return: The contents of the ref file, or None if it does not exist. """ raise NotImplementedError(self.read_loose_ref) def follow(self, name): """Follow a reference name. :return: a tuple of (refnames, sha), wheres refnames are the names of references in the chain """ contents = SYMREF + name depth = 0 refnames = [] while contents.startswith(SYMREF): refname = contents[len(SYMREF):] refnames.append(refname) contents = self.read_ref(refname) if not contents: break depth += 1 if depth > 5: raise KeyError(name) return refnames, contents def _follow(self, name): import warnings warnings.warn( "RefsContainer._follow is deprecated. Use RefsContainer.follow " "instead.", DeprecationWarning) refnames, contents = self.follow(name) if not refnames: return (None, contents) return (refnames[-1], contents) def __contains__(self, refname): if self.read_ref(refname): return True return False def __getitem__(self, name): """Get the SHA1 for a reference name. This method follows all symbolic references. """ _, sha = self.follow(name) if sha is None: raise KeyError(name) return sha def set_if_equals(self, name, old_ref, new_ref): """Set a refname to new_ref only if it currently equals old_ref. This method follows all symbolic references if applicable for the subclass, and can be used to perform an atomic compare-and-swap operation. :param name: The refname to set. :param old_ref: The old sha the refname must refer to, or None to set unconditionally. :param new_ref: The new sha the refname will refer to. :return: True if the set was successful, False otherwise. """ raise NotImplementedError(self.set_if_equals) def add_if_new(self, name, ref): """Add a new reference only if it does not already exist.""" raise NotImplementedError(self.add_if_new) def __setitem__(self, name, ref): """Set a reference name to point to the given SHA1. This method follows all symbolic references if applicable for the subclass. :note: This method unconditionally overwrites the contents of a reference. To update atomically only if the reference has not changed, use set_if_equals(). :param name: The refname to set. :param ref: The new sha the refname will refer to. """ self.set_if_equals(name, None, ref) def remove_if_equals(self, name, old_ref): """Remove a refname only if it currently equals old_ref. This method does not follow symbolic references, even if applicable for the subclass. It can be used to perform an atomic compare-and-delete operation. :param name: The refname to delete. :param old_ref: The old sha the refname must refer to, or None to delete unconditionally. :return: True if the delete was successful, False otherwise. """ raise NotImplementedError(self.remove_if_equals) def __delitem__(self, name): """Remove a refname. This method does not follow symbolic references, even if applicable for the subclass. :note: This method unconditionally deletes the contents of a reference. To delete atomically only if the reference has not changed, use remove_if_equals(). :param name: The refname to delete. """ self.remove_if_equals(name, None) def get_symrefs(self): """Get a dict with all symrefs in this container. :return: Dictionary mapping source ref to target ref """ ret = {} for src in self.allkeys(): try: dst = parse_symref_value(self.read_ref(src)) except ValueError: pass else: ret[src] = dst return ret class DictRefsContainer(RefsContainer): """RefsContainer backed by a simple dict. This container does not support symbolic or packed references and is not threadsafe. """ def __init__(self, refs): self._refs = refs self._peeled = {} def allkeys(self): return self._refs.keys() def read_loose_ref(self, name): return self._refs.get(name, None) def get_packed_refs(self): return {} def set_symbolic_ref(self, name, other): self._refs[name] = SYMREF + other def set_if_equals(self, name, old_ref, new_ref): if old_ref is not None and self._refs.get(name, ZERO_SHA) != old_ref: return False realnames, _ = self.follow(name) for realname in realnames: self._check_refname(realname) self._refs[realname] = new_ref return True def add_if_new(self, name, ref): if name in self._refs: return False self._refs[name] = ref return True def remove_if_equals(self, name, old_ref): if old_ref is not None and self._refs.get(name, ZERO_SHA) != old_ref: return False try: del self._refs[name] except KeyError: pass return True def get_peeled(self, name): return self._peeled.get(name) def _update(self, refs): """Update multiple refs; intended only for testing.""" # TODO(dborowitz): replace this with a public function that uses # set_if_equal. self._refs.update(refs) def _update_peeled(self, peeled): """Update cached peeled refs; intended only for testing.""" self._peeled.update(peeled) class InfoRefsContainer(RefsContainer): """Refs container that reads refs from a info/refs file.""" def __init__(self, f): self._refs = {} self._peeled = {} for l in f.readlines(): sha, name = l.rstrip(b'\n').split(b'\t') if name.endswith(ANNOTATED_TAG_SUFFIX): name = name[:-3] if not check_ref_format(name): raise ValueError("invalid ref name %r" % name) self._peeled[name] = sha else: if not check_ref_format(name): raise ValueError("invalid ref name %r" % name) self._refs[name] = sha def allkeys(self): return self._refs.keys() def read_loose_ref(self, name): return self._refs.get(name, None) def get_packed_refs(self): return {} def get_peeled(self, name): try: return self._peeled[name] except KeyError: return self._refs[name] class DiskRefsContainer(RefsContainer): """Refs container that reads refs from disk.""" def __init__(self, path, worktree_path=None): self.path = path self.worktree_path = worktree_path or path self._packed_refs = None self._peeled_refs = None def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self.path) def subkeys(self, base): subkeys = set() path = self.refpath(base) for root, dirs, files in os.walk(path): dir = root[len(path):].strip(os.path.sep).replace(os.path.sep, "/") for filename in files: refname = (("%s/%s" % (dir, filename)) .strip("/").encode(sys.getfilesystemencoding())) # check_ref_format requires at least one /, so we prepend the # base before calling it. if check_ref_format(base + b'/' + refname): subkeys.add(refname) for key in self.get_packed_refs(): if key.startswith(base): subkeys.add(key[len(base):].strip(b'/')) return subkeys def allkeys(self): allkeys = set() if os.path.exists(self.refpath(b'HEAD')): allkeys.add(b'HEAD') path = self.refpath(b'') for root, dirs, files in os.walk(self.refpath(b'refs')): dir = root[len(path):].strip(os.path.sep).replace(os.path.sep, "/") for filename in files: refname = ( "%s/%s" % (dir, filename)).encode( sys.getfilesystemencoding()) if check_ref_format(refname): allkeys.add(refname) allkeys.update(self.get_packed_refs()) return allkeys def refpath(self, name): """Return the disk path of a ref. """ if (getattr(self.path, "encode", None) and getattr(name, "decode", None)): name = name.decode(sys.getfilesystemencoding()) if os.path.sep != "/": name = name.replace("/", os.path.sep) # TODO: as the 'HEAD' reference is working tree specific, it # should actually not be a part of RefsContainer if name == 'HEAD': return os.path.join(self.worktree_path, name) else: return os.path.join(self.path, name) def get_packed_refs(self): """Get contents of the packed-refs file. :return: Dictionary mapping ref names to SHA1s :note: Will return an empty dictionary when no packed-refs file is present. """ # TODO: invalidate the cache on repacking if self._packed_refs is None: # set both to empty because we want _peeled_refs to be # None if and only if _packed_refs is also None. self._packed_refs = {} self._peeled_refs = {} path = os.path.join(self.path, 'packed-refs') try: f = GitFile(path, 'rb') except IOError as e: if e.errno == errno.ENOENT: return {} raise with f: first_line = next(iter(f)).rstrip() if (first_line.startswith(b'# pack-refs') and b' peeled' in first_line): for sha, name, peeled in read_packed_refs_with_peeled(f): self._packed_refs[name] = sha if peeled: self._peeled_refs[name] = peeled else: f.seek(0) for sha, name in read_packed_refs(f): self._packed_refs[name] = sha return self._packed_refs def get_peeled(self, name): """Return the cached peeled value of a ref, if available. :param name: Name of the ref to peel :return: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If the ref may point to a tag, but no cached information is available, None is returned. """ self.get_packed_refs() if self._peeled_refs is None or name not in self._packed_refs: # No cache: no peeled refs were read, or this ref is loose return None if name in self._peeled_refs: return self._peeled_refs[name] else: # Known not peelable return self[name] def read_loose_ref(self, name): """Read a reference file and return its contents. If the reference file a symbolic reference, only read the first line of the file. Otherwise, only read the first 40 bytes. :param name: the refname to read, relative to refpath :return: The contents of the ref file, or None if the file does not exist. :raises IOError: if any other error occurs """ filename = self.refpath(name) try: with GitFile(filename, 'rb') as f: header = f.read(len(SYMREF)) if header == SYMREF: # Read only the first line return header + next(iter(f)).rstrip(b'\r\n') else: # Read only the first 40 bytes return header + f.read(40 - len(SYMREF)) except IOError as e: if e.errno in (errno.ENOENT, errno.EISDIR): return None raise def _remove_packed_ref(self, name): if self._packed_refs is None: return filename = os.path.join(self.path, 'packed-refs') # reread cached refs from disk, while holding the lock f = GitFile(filename, 'wb') try: self._packed_refs = None self.get_packed_refs() if name not in self._packed_refs: return del self._packed_refs[name] if name in self._peeled_refs: del self._peeled_refs[name] write_packed_refs(f, self._packed_refs, self._peeled_refs) f.close() finally: f.abort() def set_symbolic_ref(self, name, other): """Make a ref point at another ref. :param name: Name of the ref to set :param other: Name of the ref to point at """ self._check_refname(name) self._check_refname(other) filename = self.refpath(name) try: f = GitFile(filename, 'wb') try: f.write(SYMREF + other + b'\n') except (IOError, OSError): f.abort() raise finally: f.close() def set_if_equals(self, name, old_ref, new_ref): """Set a refname to new_ref only if it currently equals old_ref. This method follows all symbolic references, and can be used to perform an atomic compare-and-swap operation. :param name: The refname to set. :param old_ref: The old sha the refname must refer to, or None to set unconditionally. :param new_ref: The new sha the refname will refer to. :return: True if the set was successful, False otherwise. """ self._check_refname(name) try: realnames, _ = self.follow(name) realname = realnames[-1] except (KeyError, IndexError): realname = name filename = self.refpath(realname) ensure_dir_exists(os.path.dirname(filename)) with GitFile(filename, 'wb') as f: if old_ref is not None: try: # read again while holding the lock orig_ref = self.read_loose_ref(realname) if orig_ref is None: orig_ref = self.get_packed_refs().get( realname, ZERO_SHA) if orig_ref != old_ref: f.abort() return False except (OSError, IOError): f.abort() raise try: f.write(new_ref + b'\n') except (OSError, IOError): f.abort() raise return True def add_if_new(self, name, ref): """Add a new reference only if it does not already exist. This method follows symrefs, and only ensures that the last ref in the chain does not exist. :param name: The refname to set. :param ref: The new sha the refname will refer to. :return: True if the add was successful, False otherwise. """ try: realnames, contents = self.follow(name) if contents is not None: return False realname = realnames[-1] except (KeyError, IndexError): realname = name self._check_refname(realname) filename = self.refpath(realname) ensure_dir_exists(os.path.dirname(filename)) with GitFile(filename, 'wb') as f: if os.path.exists(filename) or name in self.get_packed_refs(): f.abort() return False try: f.write(ref + b'\n') except (OSError, IOError): f.abort() raise return True def remove_if_equals(self, name, old_ref): """Remove a refname only if it currently equals old_ref. This method does not follow symbolic references. It can be used to perform an atomic compare-and-delete operation. :param name: The refname to delete. :param old_ref: The old sha the refname must refer to, or None to delete unconditionally. :return: True if the delete was successful, False otherwise. """ self._check_refname(name) filename = self.refpath(name) ensure_dir_exists(os.path.dirname(filename)) f = GitFile(filename, 'wb') try: if old_ref is not None: orig_ref = self.read_loose_ref(name) if orig_ref is None: orig_ref = self.get_packed_refs().get(name, ZERO_SHA) if orig_ref != old_ref: return False # may only be packed try: os.remove(filename) except OSError as e: if e.errno != errno.ENOENT: raise self._remove_packed_ref(name) finally: # never write, we just wanted the lock f.abort() return True def _split_ref_line(line): """Split a single ref line into a tuple of SHA1 and name.""" fields = line.rstrip(b'\n\r').split(b' ') if len(fields) != 2: raise PackedRefsException("invalid ref line %r" % line) sha, name = fields if not valid_hexsha(sha): raise PackedRefsException("Invalid hex sha %r" % sha) if not check_ref_format(name): raise PackedRefsException("invalid ref name %r" % name) return (sha, name) def read_packed_refs(f): """Read a packed refs file. :param f: file-like object to read from :return: Iterator over tuples with SHA1s and ref names. """ for l in f: if l.startswith(b'#'): # Comment continue if l.startswith(b'^'): raise PackedRefsException( "found peeled ref in packed-refs without peeled") yield _split_ref_line(l) def read_packed_refs_with_peeled(f): """Read a packed refs file including peeled refs. Assumes the "# pack-refs with: peeled" line was already read. Yields tuples with ref names, SHA1s, and peeled SHA1s (or None). :param f: file-like object to read from, seek'ed to the second line """ last = None - for l in f: - if l[0] == b'#': + for line in f: + if line[0] == b'#': continue - l = l.rstrip(b'\r\n') - if l.startswith(b'^'): + line = line.rstrip(b'\r\n') + if line.startswith(b'^'): if not last: raise PackedRefsException("unexpected peeled ref line") - if not valid_hexsha(l[1:]): - raise PackedRefsException("Invalid hex sha %r" % l[1:]) + if not valid_hexsha(line[1:]): + raise PackedRefsException("Invalid hex sha %r" % line[1:]) sha, name = _split_ref_line(last) last = None - yield (sha, name, l[1:]) + yield (sha, name, line[1:]) else: if last: sha, name = _split_ref_line(last) yield (sha, name, None) - last = l + last = line if last: sha, name = _split_ref_line(last) yield (sha, name, None) def write_packed_refs(f, packed_refs, peeled_refs=None): """Write a packed refs file. :param f: empty file-like object to write to :param packed_refs: dict of refname to sha of packed refs to write :param peeled_refs: dict of refname to peeled value of sha """ if peeled_refs is None: peeled_refs = {} else: f.write(b'# pack-refs with: peeled\n') for refname in sorted(packed_refs.keys()): f.write(git_line(packed_refs[refname], refname)) if refname in peeled_refs: f.write(b'^' + peeled_refs[refname] + b'\n') def read_info_refs(f): ret = {} for l in f.readlines(): (sha, name) = l.rstrip(b"\r\n").split(b"\t", 1) ret[name] = sha return ret def write_info_refs(refs, store): """Generate info refs.""" for name, sha in sorted(refs.items()): # get_refs() includes HEAD as a special case, but we don't want to # advertise it if name == b'HEAD': continue try: o = store[sha] except KeyError: continue peeled = store.peel_sha(sha) yield o.id + b'\t' + name + b'\n' if o.id != peeled.id: yield peeled.id + b'\t' + name + ANNOTATED_TAG_SUFFIX + b'\n' def is_local_branch(x): return x.startswith(b'refs/heads/') diff --git a/setup.py b/setup.py index 80a21a11..da778cf6 100755 --- a/setup.py +++ b/setup.py @@ -1,116 +1,116 @@ #!/usr/bin/python # encoding: utf-8 # Setup file for dulwich # Copyright (C) 2008-2016 Jelmer Vernooij try: from setuptools import setup, Extension except ImportError: from distutils.core import setup, Extension from distutils.core import Distribution import os import sys dulwich_version_string = '0.18.6' include_dirs = [] # Windows MSVC support if sys.platform == 'win32' and sys.version_info[:2] < (3, 6): # Include dulwich/ for fallback stdint.h include_dirs.append('dulwich') class DulwichDistribution(Distribution): def is_pure(self): if self.pure: return True def has_ext_modules(self): return not self.pure global_options = Distribution.global_options + [ ('pure', None, "use pure Python code instead of C " "extensions (slower on CPython)")] pure = False if sys.platform == 'darwin' and os.path.exists('/usr/bin/xcodebuild'): # XCode 4.0 dropped support for ppc architecture, which is hardcoded in # distutils.sysconfig import subprocess p = subprocess.Popen( ['/usr/bin/xcodebuild', '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, env={}) out, err = p.communicate() - for l in out.splitlines(): - l = l.decode("utf8") + for line in out.splitlines(): + line = line.decode("utf8") # Also parse only first digit, because 3.2.1 can't be parsed nicely - if l.startswith('Xcode') and int(l.split()[1].split('.')[0]) >= 4: + if line.startswith('Xcode') and int(line.split()[1].split('.')[0]) >= 4: os.environ['ARCHFLAGS'] = '' tests_require = ['fastimport'] if '__pypy__' not in sys.modules and not sys.platform == 'win32': tests_require.extend([ 'gevent', 'geventhttpclient', 'mock', 'setuptools>=17.1']) ext_modules = [ Extension('dulwich._objects', ['dulwich/_objects.c'], include_dirs=include_dirs), Extension('dulwich._pack', ['dulwich/_pack.c'], include_dirs=include_dirs), Extension('dulwich._diff_tree', ['dulwich/_diff_tree.c'], include_dirs=include_dirs), ] if sys.platform == 'win32': # Win32 setup breaks with non-ascii characters. author = "Jelmer Vernooij" else: author = "Jelmer Vernooij" setup(name='dulwich', description='Python Git Library', keywords='git', version=dulwich_version_string, url='https://www.dulwich.io/', license='Apachev2 or later or GPLv2', author_email='jelmer@jelmer.uk', long_description=""" Python implementation of the Git file formats and protocols, without the need to have git installed. All functionality is available in pure Python. Optional C extensions can be built for improved performance. The project is named after the part of London that Mr. and Mrs. Git live in in the particular Monty Python sketch. """, packages=['dulwich', 'dulwich.tests', 'dulwich.tests.compat', 'dulwich.contrib'], package_data={'': ['../docs/tutorial/*.txt']}, scripts=['bin/dulwich', 'bin/dul-receive-pack', 'bin/dul-upload-pack'], classifiers=[ 'Development Status :: 4 - Beta', 'License :: OSI Approved :: Apache Software License', 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3.3', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy', 'Operating System :: POSIX', 'Operating System :: Microsoft :: Windows', 'Topic :: Software Development :: Version Control', ], ext_modules=ext_modules, test_suite='dulwich.tests.test_suite', tests_require=tests_require, distclass=DulwichDistribution, include_package_data=True, )