diff options
Diffstat (limited to 'git/objects')
| -rw-r--r-- | git/objects/__init__.py | 2 | ||||
| -rw-r--r-- | git/objects/base.py | 47 | ||||
| -rw-r--r-- | git/objects/blob.py | 2 | ||||
| -rw-r--r-- | git/objects/commit.py | 98 | ||||
| -rw-r--r-- | git/objects/fun.py | 44 | ||||
| -rw-r--r-- | git/objects/submodule/base.py | 213 | ||||
| -rw-r--r-- | git/objects/submodule/root.py | 74 | ||||
| -rw-r--r-- | git/objects/submodule/util.py | 18 | ||||
| -rw-r--r-- | git/objects/tag.py | 17 | ||||
| -rw-r--r-- | git/objects/tree.py | 66 | ||||
| -rw-r--r-- | git/objects/util.py | 86 |
11 files changed, 331 insertions, 336 deletions
diff --git a/git/objects/__init__.py b/git/objects/__init__.py index 77f69d29..90fe81a8 100644 --- a/git/objects/__init__.py +++ b/git/objects/__init__.py @@ -18,4 +18,4 @@ from commit import * from tree import * __all__ = [ name for name, obj in locals().items() - if not (name.startswith('_') or inspect.ismodule(obj)) ]
\ No newline at end of file + if not (name.startswith('_') or inspect.ismodule(obj)) ] diff --git a/git/objects/base.py b/git/objects/base.py index 03b22863..9e73e2f3 100644 --- a/git/objects/base.py +++ b/git/objects/base.py @@ -12,7 +12,7 @@ from gitdb.util import ( ) import gitdb.typ as dbtyp - + _assertion_msg_format = "Created object %r whose python type %r disagrees with the acutal git object type %r" __all__ = ("Object", "IndexObject") @@ -21,17 +21,17 @@ class Object(LazyMixin): """Implements an Object which may be Blobs, Trees, Commits and Tags""" NULL_HEX_SHA = '0'*40 NULL_BIN_SHA = '\0'*20 - + TYPES = (dbtyp.str_blob_type, dbtyp.str_tree_type, dbtyp.str_commit_type, dbtyp.str_tag_type) __slots__ = ("repo", "binsha", "size" ) type = None # to be set by subclass - + def __init__(self, repo, binsha): """Initialize an object by identifying it by its binary sha. All keyword arguments will be set on demand if None. - + :param repo: repository this object is located in - + :param binsha: 20 byte SHA1""" super(Object,self).__init__() self.repo = repo @@ -44,13 +44,13 @@ class Object(LazyMixin): :return: New Object instance of a type appropriate to the object type behind id. The id of the newly created object will be a binsha even though the input id may have been a Reference or Rev-Spec - + :param id: reference, rev-spec, or hexsha - + :note: This cannot be a __new__ method as it would always call __init__ with the input id which is not necessarily a binsha.""" return repo.rev_parse(str(id)) - + @classmethod def new_from_sha(cls, repo, sha1): """ @@ -65,36 +65,36 @@ class Object(LazyMixin): inst = get_object_type_by_name(oinfo.type)(repo, oinfo.binsha) inst.size = oinfo.size return inst - + def _set_cache_(self, attr): """Retrieve object information""" - if attr == "size": + if attr == "size": oinfo = self.repo.odb.info(self.binsha) self.size = oinfo.size # assert oinfo.type == self.type, _assertion_msg_format % (self.binsha, oinfo.type, self.type) else: super(Object,self)._set_cache_(attr) - + def __eq__(self, other): """:return: True if the objects have the same SHA1""" if not hasattr(other, 'binsha'): return False return self.binsha == other.binsha - + def __ne__(self, other): """:return: True if the objects do not have the same SHA1 """ if not hasattr(other, 'binsha'): return True return self.binsha != other.binsha - + def __hash__(self): """:return: Hash of our id allowing objects to be used in dicts and sets""" return hash(self.binsha) - + def __str__(self): """:return: string of our SHA1 as understood by all git commands""" return bin_to_hex(self.binsha) - + def __repr__(self): """:return: string with pythonic representation of our object""" return '<git.%s "%s">' % (self.__class__.__name__, self.hexsha) @@ -117,16 +117,16 @@ class Object(LazyMixin): istream = self.repo.odb.stream(self.binsha) stream_copy(istream, ostream) return self - + class IndexObject(Object): """Base for all objects that can be part of the index file , namely Tree, Blob and SubModule objects""" __slots__ = ("path", "mode") - + # for compatability with iterable lists _id_attribute_ = 'path' - + def __init__(self, repo, binsha, mode=None, path=None): """Initialize a newly instanced IndexObject :param repo: is the Repo we are located in @@ -144,13 +144,13 @@ class IndexObject(Object): self.mode = mode if path is not None: self.path = path - + def __hash__(self): """:return: Hash of our path as index items are uniquely identifyable by path, not by their data !""" return hash(self.path) - + def _set_cache_(self, attr): if attr in IndexObject.__slots__: # they cannot be retrieved lateron ( not without searching for them ) @@ -158,19 +158,18 @@ class IndexObject(Object): else: super(IndexObject, self)._set_cache_(attr) # END hanlde slot attribute - + @property def name(self): """:return: Name portion of the path, effectively being the basename""" return basename(self.path) - + @property def abspath(self): """ :return: Absolute path to this index object in the file system ( as opposed to the .path field which is a path relative to the git repository ). - + The returned path will be native to the system and contains '\' on windows. """ return join_path_native(self.repo.working_tree_dir, self.path) - diff --git a/git/objects/blob.py b/git/objects/blob.py index e96555c6..fd748537 100644 --- a/git/objects/blob.py +++ b/git/objects/blob.py @@ -13,7 +13,7 @@ class Blob(base.IndexObject): """A Blob encapsulates a git blob object""" DEFAULT_MIME_TYPE = "text/plain" type = "blob" - + # valid blob modes executable_mode = 0100755 file_mode = 0100644 diff --git a/git/objects/commit.py b/git/objects/commit.py index bc437e8b..db1493d5 100644 --- a/git/objects/commit.py +++ b/git/objects/commit.py @@ -4,7 +4,7 @@ # This module is part of GitPython and is released under # the BSD License: http://www.opensource.org/licenses/bsd-license.php -from git.util import ( +from git.util import ( Actor, Iterable, Stats, @@ -37,22 +37,22 @@ __all__ = ('Commit', ) class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): """Wraps a git Commit object. - + This class will act lazily on some of its attributes and will query the value on demand only if it involves calling the git binary.""" - + # ENVIRONMENT VARIABLES # read when creating new commits env_author_date = "GIT_AUTHOR_DATE" env_committer_date = "GIT_COMMITTER_DATE" - + # CONFIGURATION KEYS conf_encoding = 'i18n.commitencoding' - + # INVARIANTS default_encoding = "UTF-8" - - + + # object configuration type = "commit" __slots__ = ("tree", @@ -60,7 +60,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): "committer", "committed_date", "committer_tz_offset", "message", "parents", "encoding", "gpgsig") _id_attribute_ = "binsha" - + def __init__(self, repo, binsha, tree=None, author=None, authored_date=None, author_tz_offset=None, committer=None, committed_date=None, committer_tz_offset=None, message=None, parents=None, encoding=None, gpgsig=None): @@ -93,7 +93,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): List or tuple of Commit objects which are our parent(s) in the commit dependency graph :return: git.Commit - + :note: Timezone information is in the same format and in the same sign as what time.altzone returns. The sign is inverted compared to git's UTC timezone.""" @@ -139,7 +139,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): def summary(self): """:return: First line of the commit message""" return self.message.split('\n', 1)[0] - + def count(self, paths='', **kwargs): """Count the number of commits reachable from this commit @@ -157,7 +157,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): return len(self.repo.git.rev_list(self.hexsha, '--', paths, **kwargs).splitlines()) else: return len(self.repo.git.rev_list(self.hexsha, **kwargs).splitlines()) - + @property def name_rev(self): @@ -192,10 +192,10 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): proc = repo.git.rev_list(rev, args, as_process=True, **kwargs) return cls._iter_from_process_or_stream(repo, proc) - + def iter_parents(self, paths='', **kwargs): """Iterate _all_ parents of this commit. - + :param paths: Optional path or list of paths limiting the Commits to those that contain at least one of the paths @@ -206,14 +206,14 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): if skip == 0: # skip ourselves skip = 1 kwargs['skip'] = skip - + return self.iter_items(self.repo, self, paths, **kwargs) @property def stats(self): """Create a git stat from changes between this commit and its first parent or from all changes done if this is the very first commit. - + :return: git.Stats""" if not self.parents: text = self.repo.git.diff_tree(self.hexsha, '--', numstat=True, root=True) @@ -237,7 +237,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): stream = proc_or_stream if not hasattr(stream,'readline'): stream = proc_or_stream.stdout - + readline = stream.readline while True: line = readline() @@ -248,7 +248,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): # split additional information, as returned by bisect for instance hexsha, rest = line.split(None, 1) # END handle extra info - + assert len(hexsha) == 40, "Invalid line: %s" % hexsha yield Commit(repo, hex_to_bin(hexsha)) # END for each line in stream @@ -256,12 +256,12 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): # due to many developers trying to fix the open file handles issue if hasattr(proc_or_stream, 'wait'): finalize_process(proc_or_stream) - - + + @classmethod def create_from_tree(cls, repo, tree, message, parent_commits=None, head=False): """Commit the given tree, creating a commit object. - + :param repo: Repo object the commit should be part of :param tree: Tree object or hex or bin sha the tree of the new commit @@ -277,9 +277,9 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): If True, the HEAD will be advanced to the new commit automatically. Else the HEAD will remain pointing on the previous commit. This could lead to undesired results when diffing files. - + :return: Commit object representing the new commit - + :note: Additional information about the committer and Author are taken from the environment or from the git configuration, see git-commit-tree for @@ -293,63 +293,63 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): parent_commits = list() # END handle parent commits # END if parent commits are unset - + # retrieve all additional information, create a commit object, and # serialize it # Generally: # * Environment variables override configuration values # * Sensible defaults are set according to the git documentation - + # COMMITER AND AUTHOR INFO cr = repo.config_reader() env = os.environ - + committer = Actor.committer(cr) author = Actor.author(cr) - + # PARSE THE DATES unix_time = int(time()) offset = altzone - + author_date_str = env.get(cls.env_author_date, '') if author_date_str: author_time, author_offset = parse_date(author_date_str) else: author_time, author_offset = unix_time, offset # END set author time - + committer_date_str = env.get(cls.env_committer_date, '') if committer_date_str: committer_time, committer_offset = parse_date(committer_date_str) else: committer_time, committer_offset = unix_time, offset # END set committer time - + # assume utf8 encoding enc_section, enc_option = cls.conf_encoding.split('.') conf_encoding = cr.get_value(enc_section, enc_option, cls.default_encoding) - - + + # if the tree is no object, make sure we create one - otherwise # the created commit object is invalid if isinstance(tree, str): tree = repo.tree(tree) # END tree conversion - + # CREATE NEW COMMIT new_commit = cls(repo, cls.NULL_BIN_SHA, tree, author, author_time, author_offset, committer, committer_time, committer_offset, message, parent_commits, conf_encoding) - + stream = StringIO() new_commit._serialize(stream) streamlen = stream.tell() stream.seek(0) - + istream = repo.odb.store(IStream(cls.type, streamlen, stream)) new_commit.binsha = istream.binsha - + if head: # need late import here, importing git at the very beginning throws # as well ... @@ -364,29 +364,29 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): repo.head.set_reference(master, logmsg='commit: Switching to %s' % master) # END handle empty repositories # END advance head handling - + return new_commit - + #{ Serializable Implementation - + def _serialize(self, stream): write = stream.write write("tree %s\n" % self.tree) for p in self.parents: write("parent %s\n" % p) - + a = self.author aname = a.name if isinstance(aname, unicode): aname = aname.encode(self.encoding) # END handle unicode in name - + c = self.committer fmt = "%s %s <%s> %s %s\n" write(fmt % ("author", aname, a.email, self.authored_date, altz_to_utctz_str(self.author_tz_offset))) - + # encode committer aname = c.name if isinstance(aname, unicode): @@ -395,7 +395,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): write(fmt % ("committer", aname, c.email, self.committed_date, altz_to_utctz_str(self.committer_tz_offset))) - + if self.encoding != self.default_encoding: write("encoding %s\n" % self.encoding) @@ -405,7 +405,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): write(" "+sigline+"\n") write("\n") - + # write plain bytes, be sure its encoded according to our encoding if isinstance(self.message, unicode): write(self.message.encode(self.encoding)) @@ -413,7 +413,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): write(self.message) # END handle encoding return self - + def _deserialize(self, stream): """:param from_rev_list: if true, the stream format is coming from the rev-list command Otherwise it is assumed to be a plain data stream from our object""" @@ -431,7 +431,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): self.parents.append(type(self)(self.repo, hex_to_bin(parent_line.split()[-1]))) # END for each parent line self.parents = tuple(self.parents) - + self.author, self.authored_date, self.author_tz_offset = parse_actor_and_date(next_line) self.committer, self.committed_date, self.committer_tz_offset = parse_actor_and_date(readline()) @@ -441,7 +441,7 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): next_line = readline() while next_line.startswith(' '): next_line = readline() - + # now we can have the encoding line, or an empty line followed by the optional # message. self.encoding = self.default_encoding @@ -474,14 +474,14 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): except UnicodeDecodeError: print >> sys.stderr, "Failed to decode author name '%s' using encoding %s" % (self.author.name, self.encoding) # END handle author's encoding - + # decode committer name try: self.committer.name = self.committer.name.decode(self.encoding) except UnicodeDecodeError: print >> sys.stderr, "Failed to decode committer name '%s' using encoding %s" % (self.committer.name, self.encoding) # END handle author's encoding - + # a stream from our data simply gives us the plain message # The end of our message stream is marked with a newline that we strip self.message = stream.read() @@ -491,5 +491,5 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable): print >> sys.stderr, "Failed to decode message '%s' using encoding %s" % (self.message, self.encoding) # END exception handling return self - + #} END serializable implementation diff --git a/git/objects/fun.py b/git/objects/fun.py index 66b7998e..a046d6d5 100644 --- a/git/objects/fun.py +++ b/git/objects/fun.py @@ -5,7 +5,7 @@ __all__ = ('tree_to_stream', 'tree_entries_from_data', 'traverse_trees_recursive 'traverse_tree_recursive') - + def tree_to_stream(entries, write): """Write the give list of entries into a stream using its write method @@ -13,13 +13,13 @@ def tree_to_stream(entries, write): :param write: write method which takes a data string""" ord_zero = ord('0') bit_mask = 7 # 3 bits set - + for binsha, mode, name in entries: mode_str = '' for i in xrange(6): mode_str = chr(((mode >> (i*3)) & bit_mask) + ord_zero) + mode_str # END for each 8 octal value - + # git slices away the first octal if its zero if mode_str[0] == '0': mode_str = mode_str[1:] @@ -46,7 +46,7 @@ def tree_entries_from_data(data): out = list() while i < len_data: mode = 0 - + # read mode # Some git versions truncate the leading 0, some don't # The type will be extracted from the mode later @@ -56,17 +56,17 @@ def tree_entries_from_data(data): mode = (mode << 3) + (ord(data[i]) - ord_zero) i += 1 # END while reading mode - + # byte is space now, skip it i += 1 - + # parse name, it is NULL separated - + ns = i while data[i] != '\0': i += 1 # END while not reached NULL - + # default encoding for strings in git is utf8 # Only use the respective unicode object if the byte stream was encoded name = data[ns:i] @@ -78,7 +78,7 @@ def tree_entries_from_data(data): if len(name) > len(name_enc): name = name_enc # END handle encoding - + # byte is NULL, get next 20 i += 1 sha = data[i:i+20] @@ -86,8 +86,8 @@ def tree_entries_from_data(data): out.append((sha, mode, name)) # END for each byte in data stream return out - - + + def _find_by_name(tree_data, name, is_dir, start_at): """return data entry matching the given name and tree mode @@ -96,7 +96,7 @@ def _find_by_name(tree_data, name, is_dir, start_at): None in the tree_data list to mark it done""" try: item = tree_data[start_at] - if item and item[2] == name and S_ISDIR(item[1]) == is_dir: + if item and item[2] == name and S_ISDIR(item[1]) == is_dir: tree_data[start_at] = None return item except IndexError: @@ -115,7 +115,7 @@ def _to_full_path(item, path_prefix): if not item: return item return (item[0], item[1], path_prefix+item[2]) - + def traverse_trees_recursive(odb, tree_shas, path_prefix): """ :return: list with entries according to the given binary tree-shas. @@ -141,10 +141,10 @@ def traverse_trees_recursive(odb, tree_shas, path_prefix): # END handle muted trees trees_data.append(data) # END for each sha to get data for - + out = list() out_append = out.append - + # find all matching entries and recursively process them together if the match # is a tree. If the match is a non-tree item, put it into the result. # Processed items will be set None @@ -157,7 +157,7 @@ def traverse_trees_recursive(odb, tree_shas, path_prefix): entries[ti] = item sha, mode, name = item # its faster to unpack is_dir = S_ISDIR(mode) # type mode bits - + # find this item in all other tree data items # wrap around, but stop one before our current index, hence # ti+nt, not ti+1+nt @@ -165,23 +165,23 @@ def traverse_trees_recursive(odb, tree_shas, path_prefix): tio = tio % nt entries[tio] = _find_by_name(trees_data[tio], name, is_dir, ii) # END for each other item data - + # if we are a directory, enter recursion if is_dir: out.extend(traverse_trees_recursive(odb, [((ei and ei[0]) or None) for ei in entries], path_prefix+name+'/')) else: out_append(tuple(_to_full_path(e, path_prefix) for e in entries)) # END handle recursion - + # finally mark it done tree_data[ii] = None # END for each item - + # we are done with one tree, set all its data empty del(tree_data[:]) # END for each tree_data chunk return out - + def traverse_tree_recursive(odb, tree_sha, path_prefix): """ :return: list of entries of the tree pointed to by the binary tree_sha. An entry @@ -192,7 +192,7 @@ def traverse_tree_recursive(odb, tree_sha, path_prefix): :param path_prefix: prefix to prepend to the front of all returned paths""" entries = list() data = tree_entries_from_data(odb.stream(tree_sha).read()) - + # unpacking/packing is faster than accessing individual items for sha, mode, name in data: if S_ISDIR(mode): @@ -200,5 +200,5 @@ def traverse_tree_recursive(odb, tree_sha, path_prefix): else: entries.append((sha, mode, path_prefix+name)) # END for each item - + return entries diff --git a/git/objects/submodule/base.py b/git/objects/submodule/base.py index 99d54076..730642ed 100644 --- a/git/objects/submodule/base.py +++ b/git/objects/submodule/base.py @@ -38,10 +38,10 @@ class UpdateProgress(RemoteProgress): derive from it and implement the ``update(...)`` message""" CLONE, FETCH, UPDWKTREE = [1 << x for x in range(RemoteProgress._num_op_codes, RemoteProgress._num_op_codes+3)] _num_op_codes = RemoteProgress._num_op_codes + 3 - + __slots__ = tuple() - - + + BEGIN = UpdateProgress.BEGIN END = UpdateProgress.END CLONE = UpdateProgress.CLONE @@ -58,25 +58,25 @@ class Submodule(util.IndexObject, Iterable, Traversable): at the path of this instance. The submodule type does not have a string type associated with it, as it exists solely as a marker in the tree and index. - + All methods work in bare and non-bare repositories.""" - + _id_attribute_ = "name" k_modules_file = '.gitmodules' k_head_option = 'branch' k_head_default = 'master' k_default_mode = stat.S_IFDIR | stat.S_IFLNK # submodules are directories with link-status - + # this is a bogus type for base class compatability type = 'submodule' - + __slots__ = ('_parent_commit', '_url', '_branch_path', '_name', '__weakref__') _cache_attrs = ('path', '_url', '_branch_path') - + def __init__(self, repo, binsha, mode=None, path=None, name = None, parent_commit=None, url=None, branch_path=None): """Initialize this instance with its attributes. We only document the ones that differ from ``IndexObject`` - + :param repo: Our parent repository :param binsha: binary sha referring to a commit in the remote repository, see url parameter :param parent_commit: see set_parent_commit() @@ -93,7 +93,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): self._branch_path = branch_path if name is not None: self._name = name - + def _set_cache_(self, attr): if attr == '_parent_commit': # set a default value, which is the root tree of the current head @@ -110,7 +110,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): else: super(Submodule, self)._set_cache_(attr) # END handle attribute name - + def _get_intermediate_items(self, item): """:return: all the submodules of our module repository""" try: @@ -118,28 +118,28 @@ class Submodule(util.IndexObject, Iterable, Traversable): except InvalidGitRepositoryError: return list() # END handle intermeditate items - + def __eq__(self, other): """Compare with another submodule""" # we may only compare by name as this should be the ID they are hashed with # Otherwise this type wouldn't be hashable # return self.path == other.path and self.url == other.url and super(Submodule, self).__eq__(other) return self._name == other._name - + def __ne__(self, other): """Compare with another submodule for inequality""" return not (self == other) - + def __hash__(self): """Hash this instance using its logical id, not the sha""" return hash(self._name) - + def __str__(self): return self._name - + def __repr__(self): return "git.%s(name=%s, path=%s, url=%s, branch_path=%s)" % (type(self).__name__, self._name, self.path, self.url, self.branch_path) - + @classmethod def _config_parser(cls, repo, parent_commit, read_only): """:return: Config Parser constrained to our submodule in read or write mode @@ -161,11 +161,11 @@ class Submodule(util.IndexObject, Iterable, Traversable): raise IOError("Could not find %s file in the tree of parent commit %s" % (cls.k_modules_file, parent_commit)) # END handle exceptions # END handle non-bare working tree - + if not read_only and (repo.bare or not parent_matches_head): raise ValueError("Cannot write blobs of 'historical' submodule configurations") # END handle writes of historical submodules - + return SubmoduleConfigParser(fp_module, read_only = read_only) def _clear_cache(self): @@ -177,29 +177,29 @@ class Submodule(util.IndexObject, Iterable, Traversable): pass # END try attr deletion # END for each name to delete - + @classmethod def _sio_modules(cls, parent_commit): """:return: Configuration file as StringIO - we only access it through the respective blob's data""" sio = StringIO(parent_commit.tree[cls.k_modules_file].data_stream.read()) sio.name = cls.k_modules_file return sio - + def _config_parser_constrained(self, read_only): """:return: Config Parser constrained to our submodule in read or write mode""" parser = self._config_parser(self.repo, self._parent_commit, read_only) parser.set_submodule(self) return SectionConstraint(parser, sm_section(self.name)) - + #{ Edit Interface - + @classmethod def add(cls, repo, name, path, url=None, branch=None, no_checkout=False): """Add a new submodule to the given repository. This will alter the index as well as the .gitmodules file, but will not create a new commit. If the submodule already exists, no matter if the configuration differs from the one provided, the existing submodule will be returned. - + :param repo: Repository instance which should receive the submodule :param name: The name/identifier for the submodule :param path: repository-relative or absolute path at which the submodule @@ -225,18 +225,18 @@ class Submodule(util.IndexObject, Iterable, Traversable): if repo.bare: raise InvalidGitRepositoryError("Cannot add submodules to bare repositories") # END handle bare repos - + path = to_native_path_linux(path) if path.endswith('/'): path = path[:-1] # END handle trailing slash - + # assure we never put backslashes into the url, as some operating systems # like it ... if url != None: url = to_native_path_linux(url) #END assure url correctness - + # INSTANTIATE INTERMEDIATE SM sm = cls(repo, cls.NULL_BIN_SHA, cls.k_default_mode, path, name) if sm.exists(): @@ -251,7 +251,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): return sm # END handle exceptions # END handle existing - + # fake-repo - we only need the functionality on the branch instance br = git.Head(repo, git.Head.to_full_path(str(branch) or cls.k_head_default)) has_module = sm.module_exists() @@ -261,7 +261,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): raise ValueError("Specified URL '%s' does not match any remote url of the repository at '%s'" % (url, sm.abspath)) # END check url # END verify urls match - + mrepo = None if url is None: if not has_module: @@ -281,13 +281,13 @@ class Submodule(util.IndexObject, Iterable, Traversable): # END setup checkout-branch mrepo = git.Repo.clone_from(url, path, **kwargs) # END verify url - + # update configuration and index index = sm.repo.index writer = sm.config_writer(index=index, write=False) writer.set_value('url', url) writer.set_value('path', path) - + sm._url = url if not branch_is_default: # store full path @@ -295,20 +295,20 @@ class Submodule(util.IndexObject, Iterable, Traversable): sm._branch_path = br.path # END handle path del(writer) - + # we deliberatly assume that our head matches our index ! pcommit = repo.head.commit sm._parent_commit = pcommit sm.binsha = mrepo.head.commit.binsha index.add([sm], write=True) - + return sm - + def update(self, recursive=False, init=True, to_latest_revision=False, progress=None, dry_run=False): """Update the repository of this submodule to point to the checkout we point at with the binsha of this instance. - + :param recursive: if True, we will operate recursively and update child- modules as well. :param init: if True, the module repository will be cloned into place if necessary @@ -326,7 +326,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): if self.repo.bare: return self #END pass in bare mode - + if progress is None: progress = UpdateProgress() #END handle progress @@ -334,12 +334,12 @@ class Submodule(util.IndexObject, Iterable, Traversable): if dry_run: prefix = "DRY-RUN: " #END handle prefix - + # to keep things plausible in dry-run mode if dry_run: mrepo = None #END init mrepo - + # ASSURE REPO IS PRESENT AND UPTODATE ##################################### try: @@ -351,7 +351,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): if i == 0: op |= BEGIN #END handle start - + progress.update(op, i, len_rmts, prefix+"Fetching remote %s of submodule %r" % (remote, self.name)) #=============================== if not dry_run: @@ -368,7 +368,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): return self # END early abort if init is not allowed import git - + # there is no git-repository yet - but delete empty paths module_path = join_path_native(self.repo.working_tree_dir, self.path) if not dry_run and os.path.isdir(module_path): @@ -378,7 +378,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): raise OSError("Module directory at %r does already exist and is non-empty" % module_path) # END handle OSError # END handle directory removal - + # don't check it out at first - nonetheless it will create a local # branch according to the remote-HEAD if possible progress.update(BEGIN|CLONE, 0, 1, prefix+"Cloning %s to %s in submodule %r" % (self.url, module_path, self.name)) @@ -386,27 +386,27 @@ class Submodule(util.IndexObject, Iterable, Traversable): mrepo = git.Repo.clone_from(self.url, module_path, n=True) #END handle dry-run progress.update(END|CLONE, 0, 1, prefix+"Done cloning to %s" % module_path) - - + + if not dry_run: # see whether we have a valid branch to checkout try: # find a remote which has our branch - we try to be flexible remote_branch = find_first_remote_branch(mrepo.remotes, self.branch_name) local_branch = mkhead(mrepo, self.branch_path) - + # have a valid branch, but no checkout - make sure we can figure # that out by marking the commit with a null_sha local_branch.set_object(util.Object(mrepo, self.NULL_BIN_SHA)) # END initial checkout + branch creation - + # make sure HEAD is not detached mrepo.head.set_reference(local_branch, logmsg="submodule: attaching head to %s" % local_branch) mrepo.head.ref.set_tracking_branch(remote_branch) except IndexError: print >> sys.stderr, "Warning: Failed to checkout tracking branch %s" % self.branch_path #END handle tracking branch - + # NOTE: Have to write the repo config file as well, otherwise # the default implementation will be offended and not update the repository # Maybe this is a good way to assure it doesn't get into our way, but @@ -414,8 +414,8 @@ class Submodule(util.IndexObject, Iterable, Traversable): self.repo.config_writer().set_value(sm_section(self.name), 'url', self.url) #END handle dry_run #END handle initalization - - + + # DETERMINE SHAS TO CHECKOUT ############################ binsha = self.binsha @@ -424,7 +424,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): # mrepo is only set if we are not in dry-run mode or if the module existed is_detached = mrepo.head.is_detached #END handle dry_run - + if mrepo is not None and to_latest_revision: msg_base = "Cannot update to latest revision in repository at %r as " % mrepo.working_dir if not is_detached: @@ -440,7 +440,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): print >> sys.stderr, "%s there was no local tracking branch" % msg_base # END handle detached head # END handle to_latest_revision option - + # update the working tree # handles dry_run if mrepo is not None and mrepo.head.commit.binsha != binsha: @@ -461,7 +461,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): #END handle dry_run progress.update(END|UPDWKTREE, 0, 1, prefix+"Done updating working tree for submodule %r" % self.name) # END update to new commit only if needed - + # HANDLE RECURSION ################## if recursive: @@ -472,15 +472,15 @@ class Submodule(util.IndexObject, Iterable, Traversable): # END handle recursive update #END handle dry run # END for each submodule - + return self - + @unbare_repo def move(self, module_path, configuration=True, module=True): """Move the submodule to a another module path. This involves physically moving the repository at our current path, changing the configuration, as well as adjusting our index entry accordingly. - + :param module_path: the path to which to move our module, given as repository-relative path. Intermediate directories will be created accordingly. If the path already exists, it must be empty. @@ -499,36 +499,36 @@ class Submodule(util.IndexObject, Iterable, Traversable): if module + configuration < 1: raise ValueError("You must specify to move at least the module or the configuration of the submodule") #END handle input - + module_path = to_native_path_linux(module_path) if module_path.endswith('/'): module_path = module_path[:-1] # END handle trailing slash - + # VERIFY DESTINATION if module_path == self.path: return self #END handle no change - + dest_path = join_path_native(self.repo.working_tree_dir, module_path) if os.path.isfile(dest_path): raise ValueError("Cannot move repository onto a file: %s" % dest_path) # END handle target files - + index = self.repo.index tekey = index.entry_key(module_path, 0) # if the target item already exists, fail if configuration and tekey in index.entries: raise ValueError("Index entry for target path did alredy exist") #END handle index key already there - + # remove existing destination if module: if os.path.exists(dest_path): if len(os.listdir(dest_path)): raise ValueError("Destination module directory was not empty") #END handle non-emptyness - + if os.path.islink(dest_path): os.remove(dest_path) else: @@ -540,7 +540,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): pass #END handle existance # END handle module - + # move the module into place if possible cur_path = self.abspath renamed_module = False @@ -548,8 +548,8 @@ class Submodule(util.IndexObject, Iterable, Traversable): os.renames(cur_path, dest_path) renamed_module = True #END move physical module - - + + # rename the index entry - have to manipulate the index directly as # git-mv cannot be used on submodules ... yeah try: @@ -563,7 +563,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): except KeyError: raise InvalidGitRepositoryError("Submodule's entry at %r did not exist" % (self.path)) #END handle submodule doesn't exist - + # update configuration writer = self.config_writer(index=index) # auto-write writer.set_value('path', module_path) @@ -576,14 +576,14 @@ class Submodule(util.IndexObject, Iterable, Traversable): # END undo module renaming raise #END handle undo rename - + return self - + @unbare_repo def remove(self, module=True, force=False, configuration=True, dry_run=False): """Remove this submodule from the repository. This will remove our entry from the .gitmodules file and the entry in the .git/config file. - + :param module: If True, the module we point to will be deleted as well. If the module is currently on a commit which is not part of any branch in the remote, if the currently checked out branch @@ -608,7 +608,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): if not (module + configuration): raise ValueError("Need to specify to delete at least the module, or the configuration") # END handle params - + # DELETE MODULE REPOSITORY ########################## if module and self.module_exists(): @@ -635,7 +635,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): if mod.is_dirty(untracked_files=True): raise InvalidGitRepositoryError("Cannot delete module at %s with any modifications, unless force is specified" % mod.working_tree_dir) # END check for dirt - + # figure out whether we have new commits compared to the remotes # NOTE: If the user pulled all the time, the remote heads might # not have been updated, so commits coming from the remote look @@ -659,13 +659,13 @@ class Submodule(util.IndexObject, Iterable, Traversable): del(rrefs) del(remote) # END for each remote - + # gently remove all submodule repositories for sm in self.children(): sm.remove(module=True, force=False, configuration=False, dry_run=dry_run) del(sm) # END for each child-submodule - + # finally delete our own submodule if not dry_run: wtd = mod.working_tree_dir @@ -674,7 +674,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): # END delete tree if possible # END handle force # END handle module deletion - + # DELETE CONFIGURATION ###################### if configuration and not dry_run: @@ -686,7 +686,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): pass #END delete entry index.write() - + # now git config - need the config intact, otherwise we can't query # inforamtion anymore self.repo.config_writer().remove_section(sm_section(self.name)) @@ -695,13 +695,13 @@ class Submodule(util.IndexObject, Iterable, Traversable): # void our data not to delay invalid access self._clear_cache() - + return self - + def set_parent_commit(self, commit, check=True): """Set this instance to use the given commit whose tree is supposed to contain the .gitmodules blob. - + :param commit: Commit'ish reference pointing at the root_tree :param check: if True, relatively expensive checks will be performed to verify validity of the submodule. @@ -714,10 +714,10 @@ class Submodule(util.IndexObject, Iterable, Traversable): if self.k_modules_file not in pctree: raise ValueError("Tree of commit %s did not contain the %s file" % (commit, self.k_modules_file)) # END handle exceptions - + prev_pc = self._parent_commit self._parent_commit = pcommit - + if check: parser = self._config_parser(self.repo, self._parent_commit, read_only=True) if not parser.has_section(sm_section(self.name)): @@ -725,19 +725,19 @@ class Submodule(util.IndexObject, Iterable, Traversable): raise ValueError("Submodule at path %r did not exist in parent commit %s" % (self.path, commit)) # END handle submodule did not exist # END handle checking mode - + # update our sha, it could have changed self.binsha = pctree[self.path].binsha - + self._clear_cache() - + return self - + @unbare_repo def config_writer(self, index=None, write=True): """:return: a config writer instance allowing you to read and write the data belonging to this submodule into the .gitmodules file. - + :param index: if not None, an IndexFile instance which should be written. defaults to the index of the Submodule's parent repository. :param write: if True, the index will be written each time a configuration @@ -753,11 +753,11 @@ class Submodule(util.IndexObject, Iterable, Traversable): writer.config._index = index writer.config._auto_write = write return writer - + #} END edit interface - + #{ Query Interface - + @unbare_repo def module(self): """:return: Repo instance initialized from the repository at our submodule path @@ -775,7 +775,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): else: raise InvalidGitRepositoryError("Repository at %r was not yet checked out" % module_path) # END handle exceptions - + def module_exists(self): """:return: True if our module exists and is a valid git repository. See module() method""" try: @@ -784,7 +784,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): except Exception: return False # END handle exception - + def exists(self): """ :return: True if the submodule exists, False otherwise. Please note that @@ -799,7 +799,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): # END if we have the attribute cache #END for each attr self._clear_cache() - + try: try: self.path @@ -814,38 +814,38 @@ class Submodule(util.IndexObject, Iterable, Traversable): # END if we have a cache # END reapply each attribute # END handle object state consistency - + @property def branch(self): """:return: The branch instance that we are to checkout :raise InvalidGitRepositoryError: if our module is not yet checked out""" return mkhead(self.module(), self._branch_path) - + @property def branch_path(self): """ :return: full (relative) path as string to the branch we would checkout from the remote and track""" return self._branch_path - + @property def branch_name(self): """:return: the name of the branch, which is the shortest possible branch name""" # use an instance method, for this we create a temporary Head instance # which uses a repository that is available at least ( it makes no difference ) return git.Head(self.repo, self._branch_path).name - + @property def url(self): """:return: The url to the repository which our module-repository refers to""" return self._url - + @property def parent_commit(self): """:return: Commit instance with the tree containing the .gitmodules file :note: will always point to the current head's commit if it was not set explicitly""" return self._parent_commit - + @property def name(self): """:return: The name of this submodule. It is used to identify it within the @@ -856,7 +856,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): easily """ return self._name - + def config_reader(self): """ :return: ConfigReader instance which allows you to qurey the configuration values @@ -866,17 +866,17 @@ class Submodule(util.IndexObject, Iterable, Traversable): :note: Should be cached by the caller and only kept as long as needed :raise IOError: If the .gitmodules file/blob could not be read""" return self._config_parser_constrained(read_only=True) - + def children(self): """ :return: IterableList(Submodule, ...) an iterable list of submodules instances which are children of this submodule or 0 if the submodule is not checked out""" return self._get_intermediate_items(self) - + #} END query interface - + #{ Iterable Interface - + @classmethod def iter_items(cls, repo, parent_commit='HEAD'): """:return: iterator yielding Submodule instances available in the given repository""" @@ -886,9 +886,9 @@ class Submodule(util.IndexObject, Iterable, Traversable): except IOError: raise StopIteration # END handle empty iterator - + rt = pc.tree # root tree - + for sms in parser.sections(): n = sm_name(sms) p = parser.get_value(sms, 'path') @@ -897,7 +897,7 @@ class Submodule(util.IndexObject, Iterable, Traversable): if parser.has_option(sms, cls.k_head_option): b = str(parser.get_value(sms, cls.k_head_option)) # END handle optional information - + # get the binsha index = repo.index try: @@ -911,15 +911,14 @@ class Submodule(util.IndexObject, Iterable, Traversable): raise InvalidGitRepositoryError("Gitmodule path %r did not exist in revision of parent commit %s" % (p, parent_commit)) # END handle keyerror # END handle critical error - + # fill in remaining info - saves time as it doesn't have to be parsed again sm._name = n sm._parent_commit = pc sm._branch_path = git.Head.to_full_path(b) sm._url = u - + yield sm # END for each section - - #} END iterable interface + #} END iterable interface diff --git a/git/objects/submodule/root.py b/git/objects/submodule/root.py index d9764b36..fb0a65c3 100644 --- a/git/objects/submodule/root.py +++ b/git/objects/submodule/root.py @@ -14,7 +14,7 @@ class RootUpdateProgress(UpdateProgress): """Utility class which adds more opcodes to the UpdateProgress""" REMOVE, PATHCHANGE, BRANCHCHANGE, URLCHANGE = [1 << x for x in range(UpdateProgress._num_op_codes, UpdateProgress._num_op_codes+4)] _num_op_codes = UpdateProgress._num_op_codes+4 - + __slots__ = tuple() BEGIN = RootUpdateProgress.BEGIN @@ -27,11 +27,11 @@ PATHCHANGE = RootUpdateProgress.PATHCHANGE class RootModule(Submodule): """A (virtual) Root of all submodules in the given repository. It can be used to more easily traverse all submodules of the master repository""" - + __slots__ = tuple() - + k_root_name = '__ROOT__' - + def __init__(self, repo): # repo, binsha, mode=None, path=None, name = None, parent_commit=None, url=None, ref=None) super(RootModule, self).__init__( @@ -44,14 +44,14 @@ class RootModule(Submodule): url = '', branch_path = git.Head.to_full_path(self.k_head_default) ) - - + + def _clear_cache(self): """May not do anything""" pass - + #{ Interface - + def update(self, previous_commit=None, recursive=True, force_remove=False, init=True, to_latest_revision=False, progress=None, dry_run=False): """Update the submodules of this repository to the current HEAD commit. @@ -60,7 +60,7 @@ class RootModule(Submodule): checked out. This works if the submodules ID does not change. Additionally it will detect addition and removal of submodules, which will be handled gracefully. - + :param previous_commit: If set to a commit'ish, the commit we should use as the previous commit the HEAD pointed to before it was set to the commit it points to now. If None, it defaults to HEAD@{1} otherwise @@ -79,17 +79,17 @@ class RootModule(Submodule): if self.repo.bare: raise InvalidGitRepositoryError("Cannot update submodules in bare repositories") # END handle bare - + if progress is None: progress = RootUpdateProgress() #END assure progress is set - + prefix = '' if dry_run: prefix = 'DRY-RUN: ' - + repo = self.repo - + # SETUP BASE COMMIT ################### cur_commit = repo.head.commit @@ -106,13 +106,13 @@ class RootModule(Submodule): else: previous_commit = repo.commit(previous_commit) # obtain commit object # END handle previous commit - - + + psms = self.list_items(repo, parent_commit=previous_commit) sms = self.list_items(repo) spsms = set(psms) ssms = set(sms) - + # HANDLE REMOVALS ################### rrsm = (spsms - ssms) @@ -122,7 +122,7 @@ class RootModule(Submodule): if i == 0: op |= BEGIN #END handle begin - + # fake it into thinking its at the current commit to allow deletion # of previous module. Trigger the cache to be updated before that progress.update(op, i, len_rrsm, prefix+"Removing submodule %r at %s" % (rsm.name, rsm.abspath)) @@ -130,13 +130,13 @@ class RootModule(Submodule): if not dry_run: rsm.remove(configuration=False, module=True, force=force_remove) #END handle dry-run - + if i == len_rrsm-1: op |= END #END handle end progress.update(op, i, len_rrsm, prefix+"Done removing submodule %r" % rsm.name) # END for each removed submodule - + # HANDLE PATH RENAMES ##################### # url changes + branch changes @@ -145,7 +145,7 @@ class RootModule(Submodule): for i, csm in enumerate(csms): psm = psms[csm.name] sm = sms[csm.name] - + #PATH CHANGES ############## if sm.path != psm.path and psm.module_exists(): @@ -156,7 +156,7 @@ class RootModule(Submodule): #END handle dry_run progress.update(END|PATHCHANGE, i, len_csms, prefix+"Done moving repository of submodule %r" % sm.name) # END handle path changes - + if sm.module_exists(): # HANDLE URL CHANGE ################### @@ -167,22 +167,22 @@ class RootModule(Submodule): nn = '__new_origin__' smm = sm.module() rmts = smm.remotes - + # don't do anything if we already have the url we search in place if len([r for r in rmts if r.url == sm.url]) == 0: progress.update(BEGIN|URLCHANGE, i, len_csms, prefix+"Changing url of submodule %r from %s to %s" % (sm.name, psm.url, sm.url)) - + if not dry_run: assert nn not in [r.name for r in rmts] smr = smm.create_remote(nn, sm.url) smr.fetch(progress=progress) - + # If we have a tracking branch, it should be available # in the new remote as well. if len([r for r in smr.refs if r.remote_head == sm.branch_name]) == 0: raise ValueError("Submodule branch named %r was not available in new submodule remote at %r" % (sm.branch_name, sm.url)) # END head is not detached - + # now delete the changed one rmt_for_deletion = None for remote in rmts: @@ -191,7 +191,7 @@ class RootModule(Submodule): break # END if urls match # END for each remote - + # if we didn't find a matching remote, but have exactly one, # we can safely use this one if rmt_for_deletion is None: @@ -206,7 +206,7 @@ class RootModule(Submodule): raise InvalidGitRepositoryError("Couldn't find original remote-repo at url %r" % psm.url) #END handle one single remote # END handle check we found a remote - + orig_name = rmt_for_deletion.name smm.delete_remote(rmt_for_deletion) # NOTE: Currently we leave tags from the deleted remotes @@ -215,10 +215,10 @@ class RootModule(Submodule): # another project ). At some point, one might want to clean # it up, but the danger is high to remove stuff the user # has added explicitly - + # rename the new remote back to what it was smr.rename(orig_name) - + # early on, we verified that the our current tracking branch # exists in the remote. Now we have to assure that the # sha we point to is still contained in the new remote @@ -232,7 +232,7 @@ class RootModule(Submodule): break # END traverse all commits in search for sha # END for each commit - + if not found: # adjust our internal binsha to use the one of the remote # this way, it will be checked out in the next step @@ -241,13 +241,13 @@ class RootModule(Submodule): print >> sys.stderr, "WARNING: Current sha %s was not contained in the tracking branch at the new remote, setting it the the remote's tracking branch" % sm.hexsha sm.binsha = rref.commit.binsha #END reset binsha - + #NOTE: All checkout is performed by the base implementation of update #END handle dry_run progress.update(END|URLCHANGE, i, len_csms, prefix+"Done adjusting url of submodule %r" % (sm.name)) # END skip remote handling if new url already exists in module # END handle url - + # HANDLE PATH CHANGES ##################### if sm.branch_path != psm.branch_path: @@ -263,7 +263,7 @@ class RootModule(Submodule): # ... or reuse the existing one tbr = git.Head(smm, sm.branch_path) #END assure tracking branch exists - + tbr.set_tracking_branch(find_first_remote_branch(smmr, sm.branch_name)) # figure out whether the previous tracking branch contains # new commits compared to the other one, if not we can @@ -278,22 +278,22 @@ class RootModule(Submodule): # current remotes, this just means we can't handle it pass # END exception handling - + #NOTE: All checkout is done in the base implementation of update #END handle dry_run - + progress.update(END|BRANCHCHANGE, i, len_csms, prefix+"Done changing branch of submodule %r" % sm.name) #END handle branch #END handle # END for each common submodule - + # FINALLY UPDATE ALL ACTUAL SUBMODULES ###################################### for sm in sms: # update the submodule using the default method sm.update(recursive=False, init=init, to_latest_revision=to_latest_revision, progress=progress, dry_run=dry_run) - + # update recursively depth first - question is which inconsitent # state will be better in case it fails somewhere. Defective branch # or defective depth. The RootSubmodule type will never process itself, diff --git a/git/objects/submodule/util.py b/git/objects/submodule/util.py index 492d9dbe..237321e2 100644 --- a/git/objects/submodule/util.py +++ b/git/objects/submodule/util.py @@ -17,11 +17,11 @@ def sm_name(section): """:return: name of the submodule as parsed from the section name""" section = section.strip() return section[11:-1] - + def mkhead(repo, path): """:return: New branch/head instance""" return git.Head(repo, git.Head.to_full_path(path)) - + def unbare_repo(func): """Methods with this decorator raise InvalidGitRepositoryError if they encounter a bare repository""" @@ -33,7 +33,7 @@ def unbare_repo(func): # END wrapper wrapper.__name__ = func.__name__ return wrapper - + def find_first_remote_branch(remotes, branch_name): """Find the remote branch matching the name of the given branch or raise InvalidGitRepositoryError""" for remote in remotes: @@ -44,7 +44,7 @@ def find_first_remote_branch(remotes, branch_name): # END exception handling #END for remote raise InvalidGitRepositoryError("Didn't find remote branch %r in any of the given remotes", branch_name) - + #} END utilities @@ -56,16 +56,16 @@ class SubmoduleConfigParser(GitConfigParser): with the new data, if we have written into a stream. Otherwise it will add the local file to the index to make it correspond with the working tree. Additionally, the cache must be cleared - + Please note that no mutating method will work in bare mode """ - + def __init__(self, *args, **kwargs): self._smref = None self._index = None self._auto_write = True super(SubmoduleConfigParser, self).__init__(*args, **kwargs) - + #{ Interface def set_submodule(self, submodule): """Set this instance's submodule. It must be called before @@ -77,7 +77,7 @@ class SubmoduleConfigParser(GitConfigParser): assert self._smref is not None # should always have a file here assert not isinstance(self._file_or_files, StringIO) - + sm = self._smref() if sm is not None: index = self._index @@ -89,7 +89,7 @@ class SubmoduleConfigParser(GitConfigParser): # END handle weakref #} END interface - + #{ Overridden Methods def write(self): rval = super(SubmoduleConfigParser, self).write() diff --git a/git/objects/tag.py b/git/objects/tag.py index d0b5a11a..b34c5945 100644 --- a/git/objects/tag.py +++ b/git/objects/tag.py @@ -17,11 +17,11 @@ class TagObject(base.Object): """Non-Lightweight tag carrying additional information about an object we are pointing to.""" type = "tag" __slots__ = ( "object", "tag", "tagger", "tagged_date", "tagger_tz_offset", "message" ) - + def __init__(self, repo, binsha, object=None, tag=None, tagger=None, tagged_date=None, tagger_tz_offset=None, message=None): """Initialize a tag object with additional data - + :param repo: repository this object is located in :param binsha: 20 byte SHA1 :param object: Object instance of object we are pointing to @@ -45,22 +45,22 @@ class TagObject(base.Object): self.tagger_tz_offset = tagger_tz_offset if message is not None: self.message = message - + def _set_cache_(self, attr): """Cache all our attributes at once""" if attr in TagObject.__slots__: ostream = self.repo.odb.stream(self.binsha) lines = ostream.read().splitlines() - + obj, hexsha = lines[0].split(" ") # object <hexsha> type_token, type_name = lines[1].split(" ") # type <type_name> self.object = get_object_type_by_name(type_name)(self.repo, hex_to_bin(hexsha)) - + self.tag = lines[2][4:] # tag <tag name> - + tagger_info = lines[3]# tagger <actor> <date> self.tagger, self.tagged_date, self.tagger_tz_offset = parse_actor_and_date(tagger_info) - + # line 4 empty - it could mark the beginning of the next header # in case there really is no message, it would not exist. Otherwise # a newline separates header from message @@ -71,6 +71,3 @@ class TagObject(base.Object): # END check our attributes else: super(TagObject, self)._set_cache_(attr) - - - diff --git a/git/objects/tree.py b/git/objects/tree.py index d1e827f5..92b0feca 100644 --- a/git/objects/tree.py +++ b/git/objects/tree.py @@ -23,14 +23,14 @@ __all__ = ("TreeModifier", "Tree") class TreeModifier(object): """A utility class providing methods to alter the underlying cache in a list-like fashion. - + Once all adjustments are complete, the _cache, which really is a refernce to the cache of a tree, will be sorted. Assuring it will be in a serializable state""" __slots__ = '_cache' - + def __init__(self, cache): self._cache = cache - + def _index_by_name(self, name): """:return: index of an item with name, or -1 if not found""" for i, t in enumerate(self._cache): @@ -39,7 +39,7 @@ class TreeModifier(object): # END found item # END for each item in cache return -1 - + #{ Interface def set_done(self): """Call this method once you are done modifying the tree information. @@ -49,14 +49,14 @@ class TreeModifier(object): self._cache.sort(key=lambda t: t[2]) # sort by name return self #} END interface - + #{ Mutators def add(self, sha, mode, name, force=False): """Add the given item to the tree. If an item with the given name already exists, nothing will be done, but a ValueError will be raised if the sha and mode of the existing item do not match the one you add, unless force is True - + :param sha: The 20 or 40 byte sha of the item to add :param mode: int representing the stat compatible mode of the item :param force: If True, an item with your name and information will overwrite @@ -66,7 +66,7 @@ class TreeModifier(object): raise ValueError("Name must not contain '/' characters") if (mode >> 12) not in Tree._map_id_to_type: raise ValueError("Invalid object type according to mode %o" % mode) - + sha = to_bin_sha(sha) index = self._index_by_name(name) item = (sha, mode, name) @@ -83,52 +83,52 @@ class TreeModifier(object): # END handle force # END handle name exists return self - + def add_unchecked(self, binsha, mode, name): """Add the given item to the tree, its correctness is assumed, which puts the caller into responsibility to assure the input is correct. For more information on the parameters, see ``add`` :param binsha: 20 byte binary sha""" self._cache.append((binsha, mode, name)) - + def __delitem__(self, name): """Deletes an item with the given name if it exists""" index = self._index_by_name(name) if index > -1: del(self._cache[index]) - + #} END mutators class Tree(IndexObject, diff.Diffable, util.Traversable, util.Serializable): """Tree objects represent an ordered list of Blobs and other Trees. - + ``Tree as a list``:: - + Access a specific blob using the tree['filename'] notation. - + You may as well access by index blob = tree[0] """ - + type = "tree" __slots__ = "_cache" - + # actual integer ids for comparison commit_id = 016 # equals stat.S_IFDIR | stat.S_IFLNK - a directory link blob_id = 010 symlink_id = 012 tree_id = 004 - + _map_id_to_type = { commit_id : Submodule, blob_id : Blob, symlink_id : Blob # tree id added once Tree is defined } - - + + def __init__(self, repo, binsha, mode=tree_id<<12, path=None): super(Tree, self).__init__(repo, binsha, mode, path) @@ -161,7 +161,7 @@ class Tree(IndexObject, diff.Diffable, util.Traversable, util.Serializable): def __div__(self, file): """Find the named object in this tree's contents :return: ``git.Blob`` or ``git.Tree`` or ``git.Submodule`` - + :raise KeyError: if given file or tree does not exist in tree""" msg = "Blob or Tree named %r not found" if '/' in file: @@ -195,7 +195,7 @@ class Tree(IndexObject, diff.Diffable, util.Traversable, util.Serializable): def trees(self): """:return: list(Tree, ...) list of trees directly below this tree""" return [ i for i in self if i.type == "tree" ] - + @property def blobs(self): """:return: list(Blob, ...) list of blobs directly below this tree""" @@ -220,26 +220,26 @@ class Tree(IndexObject, diff.Diffable, util.Traversable, util.Serializable): # List protocol def __getslice__(self, i, j): return list(self._iter_convert_to_object(self._cache[i:j])) - + def __iter__(self): return self._iter_convert_to_object(self._cache) - + def __len__(self): return len(self._cache) - + def __getitem__(self, item): if isinstance(item, int): info = self._cache[item] return self._map_id_to_type[info[1] >> 12](self.repo, info[0], info[1], join_path(self.path, info[2])) - + if isinstance(item, basestring): # compatability return self.__div__(item) # END index is basestring - + raise TypeError( "Invalid index type: %r" % item ) - - + + def __contains__(self, item): if isinstance(item, IndexObject): for info in self._cache: @@ -249,7 +249,7 @@ class Tree(IndexObject, diff.Diffable, util.Traversable, util.Serializable): # END for each entry # END handle item is index object # compatability - + # treat item as repo-relative path path = self.path for info in self._cache: @@ -257,10 +257,10 @@ class Tree(IndexObject, diff.Diffable, util.Traversable, util.Serializable): return True # END for each item return False - + def __reversed__(self): return reversed(self._iter_convert_to_object(self._cache)) - + def _serialize(self, stream): """Serialize this tree into the stream. Please note that we will assume our tree data to be in a sorted state. If this is not the case, serialization @@ -268,12 +268,12 @@ class Tree(IndexObject, diff.Diffable, util.Traversable, util.Serializable): by algorithms""" tree_to_stream(self._cache, stream.write) return self - + def _deserialize(self, stream): self._cache = tree_entries_from_data(stream.read()) return self - - + + # END tree # finalize map definition diff --git a/git/objects/util.py b/git/objects/util.py index cdf72bed..f9dffd81 100644 --- a/git/objects/util.py +++ b/git/objects/util.py @@ -40,9 +40,9 @@ def get_object_type_by_name(object_type_name): """ :return: type suitable to handle the given object type name. Use the type to create new instances. - + :param object_type_name: Member of TYPES - + :raise ValueError: In case object_type_name is unknown""" if object_type_name == "commit": import commit @@ -58,14 +58,14 @@ def get_object_type_by_name(object_type_name): return tree.Tree else: raise ValueError("Cannot handle unknown object type: %s" % object_type_name) - + def utctz_to_altz(utctz): """we convert utctz to the timezone in seconds, it is the format time.altzone returns. Git stores it as UTC timezone which has the opposite sign as well, which explains the -1 * ( that was made explicit here ) :param utctz: git utc timezone string, i.e. +0200""" return -1 * int(float(utctz)/100*3600) - + def altz_to_utctz_str(altz): """As above, but inverses the operation, returning a string that can be used in commit objects""" @@ -74,7 +74,7 @@ def altz_to_utctz_str(altz): utcs = "0"*(4-len(utcs)) + utcs prefix = (utci < 0 and '-') or '+' return prefix + utcs - + def verify_utctz(offset): """:raise ValueError: if offset is incorrect @@ -95,12 +95,12 @@ def verify_utctz(offset): def parse_date(string_date): """ Parse the given date as one of the following - + * Git internal format: timestamp offset * RFC 2822: Thu, 07 Apr 2005 22:13:13 +0200. * ISO 8601 2005-04-07T22:13:13 The T can be a space as well - + :return: Tuple(int(timestamp), int(offset)), both in seconds since epoch :raise ValueError: If the format could not be understood :note: Date can also be YYYY.MM.DD, MM/DD/YYYY and DD.MM.YYYY""" @@ -116,7 +116,7 @@ def parse_date(string_date): offset = verify_utctz(string_date[-5:]) string_date = string_date[:-6] # skip space as well # END split timezone info - + # now figure out the date and time portion - split time date_formats = list() splitter = -1 @@ -129,22 +129,22 @@ def parse_date(string_date): date_formats.append("%Y.%m.%d") date_formats.append("%m/%d/%Y") date_formats.append("%d.%m.%Y") - + splitter = string_date.rfind('T') if splitter == -1: splitter = string_date.rfind(' ') # END handle 'T' and ' ' # END handle rfc or iso - + assert splitter > -1 - + # split date and time time_part = string_date[splitter+1:] # skip space date_part = string_date[:splitter] - + # parse time tstruct = time.strptime(time_part, "%H:%M:%S") - + for fmt in date_formats: try: dtstruct = time.strptime(date_part, fmt) @@ -156,7 +156,7 @@ def parse_date(string_date): continue # END exception handling # END for each fmt - + # still here ? fail raise ValueError("no format matched") # END handle format @@ -164,16 +164,16 @@ def parse_date(string_date): raise ValueError("Unsupported date format: %s" % string_date) # END handle exceptions - + # precompiled regex _re_actor_epoch = re.compile(r'^.+? (.*) (\d+) ([+-]\d+).*$') _re_only_actor = re.compile(r'^.+? (.*)$') def parse_actor_and_date(line): """Parse out the actor (author or committer) info from a line like:: - + author Tom Preston-Werner <tom@mojombo.com> 1191999972 -0700 - + :return: [Actor, int_seconds_since_epoch, int_timezone_offset]""" actor, epoch, offset = '', 0, 0 m = _re_actor_epoch.search(line) @@ -188,10 +188,10 @@ def parse_actor_and_date(line): #{ Classes - + class ProcessStreamAdapter(object): """Class wireing all calls to the contained Process instance. - + Use this type to hide the underlying process to provide access only to a specified stream. The process is usually wrapped into an AutoInterrupt class to kill it if the instance goes out of scope.""" @@ -199,18 +199,18 @@ class ProcessStreamAdapter(object): def __init__(self, process, stream_name): self._proc = process self._stream = getattr(process, stream_name) - + def __getattr__(self, attr): return getattr(self._stream, attr) - - + + class Traversable(object): """Simple interface to perforam depth-first or breadth-first traversals into one direction. Subclasses only need to implement one function. Instances of the Subclass must be hashable""" __slots__ = tuple() - + @classmethod def _get_intermediate_items(cls, item): """ @@ -219,7 +219,7 @@ class Traversable(object): Must be implemented in subclass """ raise NotImplementedError("To be implemented in subclass") - + def list_traverse(self, *args, **kwargs): """ :return: IterableList with the results of the traversal as produced by @@ -227,36 +227,36 @@ class Traversable(object): out = IterableList(self._id_attribute_) out.extend(self.traverse(*args, **kwargs)) return out - + def traverse( self, predicate = lambda i,d: True, prune = lambda i,d: False, depth = -1, branch_first=True, visit_once = True, ignore_self=1, as_edge = False ): """:return: iterator yieling of items found when traversing self - + :param predicate: f(i,d) returns False if item i at depth d should not be included in the result - + :param prune: f(i,d) return True if the search should stop at item i at depth d. Item i will not be returned. - + :param depth: define at which level the iteration should not go deeper if -1, there is no limit if 0, you would effectively only get self, the root of the iteration i.e. if 1, you would only get the first level of predessessors/successors - + :param branch_first: if True, items will be returned branch first, otherwise depth first - + :param visit_once: if True, items will only be returned once, although they might be encountered several times. Loops are prevented that way. - + :param ignore_self: if True, self will be ignored and automatically pruned from the result. Otherwise it will be the first item to be returned. If as_edge is True, the source of the first edge is None - + :param as_edge: if True, return a pair of items, first being the source, second the destinatination, i.e. tuple(src, dest) with the edge spanning from @@ -264,7 +264,7 @@ class Traversable(object): visited = set() stack = Deque() stack.append( ( 0 ,self, None ) ) # self is always depth level 0 - + def addToStack( stack, item, branch_first, depth ): lst = self._get_intermediate_items( item ) if not lst: @@ -275,44 +275,44 @@ class Traversable(object): reviter = ( ( depth , lst[i], item ) for i in range( len( lst )-1,-1,-1) ) stack.extend( reviter ) # END addToStack local method - + while stack: d, item, src = stack.pop() # depth of item, item, item_source - + if visit_once and item in visited: continue - + if visit_once: visited.add(item) - + rval = ( as_edge and (src, item) ) or item if prune( rval, d ): continue - + skipStartItem = ignore_self and ( item is self ) if not skipStartItem and predicate( rval, d ): yield rval - + # only continue to next level if this is appropriate ! nd = d + 1 if depth > -1 and nd > depth: continue - + addToStack( stack, item, branch_first, nd ) # END for each item on work stack - + class Serializable(object): """Defines methods to serialize and deserialize objects from and into a data stream""" __slots__ = tuple() - + def _serialize(self, stream): """Serialize the data of this object into the given data stream :note: a serialized object would ``_deserialize`` into the same objet :param stream: a file-like object :return: self""" raise NotImplementedError("To be implemented in subclass") - + def _deserialize(self, stream): """Deserialize all information regarding this object from the stream :param stream: a file-like object |