def _pack_info(self, sha):
""":return: tuple(entity, index) for an item at the given sha
:param sha: 20 or 40 byte sha
:raise BadObject:
**Note:** This method is not thread-safe, but may be hit in multi-threaded
operation. The worst thing that can happen though is a counter that
was not incremented, or the list being in wrong order. So we safe
the time for locking here, lets see how that goes"""
# presort ?
if self._hit_count % self._sort_interval == 0:
self._sort_entities()
# END update sorting
for item in self._entities:
index = item[2](sha)
if index is not None:
item[0] += 1 # one hit for you
self._hit_count += 1 # general hit count
return (item[1], index)
# END index found in pack
# END for each item
# no hit, see whether we have to update packs
# NOTE: considering packs don't change very often, we safe this call
# and leave it to the super-caller to trigger that
raise BadObject(sha)
def name_to_object(repo, name):
""":return: object specified by the given name, hexshas ( short and long )
as well as references are supported"""
hexsha = None
# is it a hexsha ? Try the most common ones, which is 7 to 40
if repo.re_hexsha_shortened.match(name):
if len(name) != 40:
# find long sha for short sha
hexsha = short_to_long(repo.odb, name)
else:
hexsha = name
# END handle short shas
else:
for base in ('%s', 'refs/%s', 'refs/tags/%s', 'refs/heads/%s',
'refs/remotes/%s', 'refs/remotes/%s/HEAD'):
try:
hexsha = SymbolicReference.dereference_recursive(
repo, base % name)
break
except ValueError:
pass
# END for each base
# END handle hexsha
# tried everything ? fail
if hexsha is None:
raise BadObject(name)
# END assert hexsha was found
return Object.new_from_sha(repo, hex_to_bin(hexsha))
def partial_to_complete_sha(self, partial_binsha, canonical_length):
""":return: 20 byte sha as inferred by the given partial binary sha
:param partial_binsha: binary sha with less than 20 bytes
:param canonical_length: length of the corresponding canonical representation.
It is required as binary sha's cannot display whether the original hex sha
had an odd or even number of characters
:raise AmbiguousObjectName:
:raise BadObject: """
candidate = None
for item in self._entities:
item_index = item[1].index().partial_sha_to_index(
partial_binsha, canonical_length)
if item_index is not None:
sha = item[1].index().sha(item_index)
if candidate and candidate != sha:
raise AmbiguousObjectName(partial_binsha)
candidate = sha
# END handle full sha could be found
# END for each entity
if candidate:
return candidate
# still not found ?
raise BadObject(partial_binsha)
def name_to_object(repo, name, return_ref=False):
"""
:return: object specified by the given name, hexshas ( short and long )
as well as references are supported
:param return_ref: if name specifies a reference, we will return the reference
instead of the object. Otherwise it will raise BadObject
"""
hexsha = None
# is it a hexsha ? Try the most common ones, which is 7 to 40
if repo.re_hexsha_shortened.match(name):
if len(name) != 40:
# find long sha for short sha
hexsha = short_to_long(repo.odb, name)
else:
hexsha = name
# END handle short shas
#END find sha if it matches
# if we couldn't find an object for what seemed to be a short hexsha
# try to find it as reference anyway, it could be named 'aaa' for instance
if hexsha is None:
for base in ('%s', 'refs/%s', 'refs/tags/%s', 'refs/heads/%s',
'refs/remotes/%s', 'refs/remotes/%s/HEAD'):
try:
hexsha = SymbolicReference.dereference_recursive(
repo, base % name)
if return_ref:
return SymbolicReference(repo, base % name)
#END handle symbolic ref
break
except ValueError:
pass
# END for each base
# END handle hexsha
# didn't find any ref, this is an error
if return_ref:
raise BadObject("Couldn't find reference named %r" % name)
#END handle return ref
# tried everything ? fail
if hexsha is None:
raise BadObject(name)
# END assert hexsha was found
return Object.new_from_sha(repo, hex_to_bin(hexsha))
def stream(self, sha):
try:
ostream = self._cache[sha]
# rewind stream for the next one to read
ostream.stream.seek(0)
return ostream
except KeyError:
raise BadObject(sha)
def _map_loose_object(self, sha):
"""
:return: memory map of that file to allow random read access
:raise BadObject: if object could not be located"""
db_path = self.db_path(self.object_path(bin_to_hex(sha)))
try:
return file_contents_ro_filepath(db_path, flags=self._fd_open_flags)
except OSError as e:
if e.errno != ENOENT:
# try again without noatime
try:
return file_contents_ro_filepath(db_path)
except OSError:
raise BadObject(sha)
# didn't work because of our flag, don't try it again
self._fd_open_flags = 0
else:
raise BadObject(sha)
def partial_to_complete_sha_hex(self, partial_hexsha: str) -> bytes:
""":return: Full binary 20 byte sha from the given partial hexsha
:raise AmbiguousObjectName:
:raise BadObject:
:note: currently we only raise BadObject as git does not communicate
AmbiguousObjects separately"""
try:
hexsha, _typename, _size = self._git.get_object_header(partial_hexsha)
return hex_to_bin(hexsha)
except (GitCommandError, ValueError) as e:
raise BadObject(partial_hexsha) from e
def _object(self, sha, as_stream, index=-1):
""":return: OInfo or OStream object providing information about the given sha
:param index: if not -1, its assumed to be the sha's index in the IndexFile"""
# its a little bit redundant here, but it needs to be efficient
if index < 0:
index = self._sha_to_index(sha)
if sha is None:
sha = self._index.sha(index)
# END assure sha is present ( in output )
offset = self._index.offset(index)
type_id, uncomp_size, data_rela_offset = pack_object_header_info(
buffer(self._pack._data, offset))
if as_stream:
if type_id not in delta_types:
packstream = self._pack.stream(offset)
return OStream(sha, packstream.type, packstream.size,
packstream.stream)
# END handle non-deltas
# produce a delta stream containing all info
# To prevent it from applying the deltas when querying the size,
# we extract it from the delta stream ourselves
streams = self.collect_streams_at_offset(offset)
buf = streams[0].read(512)
offset, src_size = msb_size(buf)
offset, target_size = msb_size(buf, offset)
streams[0].stream.seek(
0) # assure it can be read by the delta reader
dstream = DeltaApplyReader.new(streams)
return OStream(sha, dstream.type, target_size, dstream)
else:
if type_id not in delta_types:
return OInfo(sha, type_id_to_type_map[type_id], uncomp_size)
# END handle non-deltas
# deltas are a little tougher - unpack the first bytes to obtain
# the actual target size, as opposed to the size of the delta data
streams = self.collect_streams_at_offset(offset)
buf = streams[0].read(512)
offset, src_size = msb_size(buf)
offset, target_size = msb_size(buf, offset)
# collect the streams to obtain the actual object type
if streams[-1].type_id in delta_types:
raise BadObject(sha, "Could not resolve delta object")
return OInfo(sha, streams[-1].type, target_size)
def partial_to_complete_sha_hex(self, partial_hexsha):
""":return: 20 byte binary sha1 string which matches the given name uniquely
:param name: hexadecimal partial name
:raise AmbiguousObjectName:
:raise BadObject: """
candidate = None
for binsha in self.sha_iter():
if bin_to_hex(binsha).startswith(partial_hexsha):
# it can't ever find the same object twice
if candidate is not None:
raise AmbiguousObjectName(partial_hexsha)
candidate = binsha
# END for each object
if candidate is None:
raise BadObject(partial_hexsha)
return candidate
def readable_db_object_path(self, hexsha):
"""
:return: readable object path to the object identified by hexsha
:raise BadObject: If the object file does not exist"""
try:
return self._hexsha_to_file[hexsha]
except KeyError:
pass
# END ignore cache misses
# try filesystem
path = self.db_path(self.object_path(hexsha))
if exists(path):
self._hexsha_to_file[hexsha] = path
return path
# END handle cache
raise BadObject(hexsha)
def _db_query(self, sha):
""":return: database containing the given 20 byte sha
:raise BadObject:"""
# most databases use binary representations, prevent converting
# it everytime a database is being queried
try:
return self._db_cache[sha]
except KeyError:
pass
# END first level cache
for db in self._dbs:
if db.has_object(sha):
self._db_cache[sha] = db
return db
# END for each database
raise BadObject(sha)
def partial_to_complete_sha_hex(self, partial_hexsha):
"""
:return: 20 byte binary sha1 from the given less-than-40 byte hexsha
:param partial_hexsha: hexsha with less than 40 byte
:raise AmbiguousObjectName: """
databases = list()
_databases_recursive(self, databases)
len_partial_hexsha = len(partial_hexsha)
if len_partial_hexsha % 2 != 0:
partial_binsha = hex_to_bin(partial_hexsha + "0")
else:
partial_binsha = hex_to_bin(partial_hexsha)
# END assure successful binary conversion
candidate = None
for db in databases:
full_bin_sha = None
try:
if hasattr(db, 'partial_to_complete_sha_hex'):
full_bin_sha = db.partial_to_complete_sha_hex(
partial_hexsha)
else:
full_bin_sha = db.partial_to_complete_sha(
partial_binsha, len_partial_hexsha)
# END handle database type
except BadObject:
continue
# END ignore bad objects
if full_bin_sha:
if candidate and candidate != full_bin_sha:
raise AmbiguousObjectName(partial_hexsha)
candidate = full_bin_sha
# END handle candidate
# END for each db
if not candidate:
raise BadObject(partial_binsha)
return candidate
def rev_parse(repo, rev):
"""
:return: Object at the given revision, either Commit, Tag, Tree or Blob
:param rev: git-rev-parse compatible revision specification, please see
http://www.kernel.org/pub/software/scm/git/docs/git-rev-parse.html
for details
:note: Currently there is no access to the rev-log, rev-specs may only contain
topological tokens such ~ and ^.
:raise BadObject: if the given revision could not be found"""
if '@' in rev:
raise ValueError("There is no rev-log support yet")
# colon search mode ?
if rev.startswith(':/'):
# colon search mode
raise NotImplementedError("commit by message search ( regex )")
# END handle search
obj = None
output_type = "commit"
start = 0
parsed_to = 0
lr = len(rev)
while start < lr:
if rev[start] not in "^~:":
start += 1
continue
# END handle start
if obj is None:
# token is a rev name
obj = name_to_object(repo, rev[:start])
# END initialize obj on first token
token = rev[start]
start += 1
# try to parse {type}
if start < lr and rev[start] == '{':
end = rev.find('}', start)
if end == -1:
raise ValueError("Missing closing brace to define type in %s" %
rev)
output_type = rev[start + 1:end] # exclude brace
# handle type
if output_type == 'commit':
pass # default
elif output_type == 'tree':
try:
obj = to_commit(obj).tree
except (AttributeError, ValueError):
pass # error raised later
# END exception handling
elif output_type in ('', 'blob'):
if obj.type == 'tag':
obj = deref_tag(obj)
else:
# cannot do anything for non-tags
pass
# END handle tag
else:
raise ValueError("Invalid output type: %s ( in %s )" %
(output_type, rev))
# END handle output type
# empty output types don't require any specific type, its just about dereferencing tags
if output_type and obj.type != output_type:
raise ValueError(
"Could not accomodate requested object type %r, got %s" %
(output_type, obj.type))
# END verify ouput type
start = end + 1 # skip brace
parsed_to = start
continue
# END parse type
# try to parse a number
num = 0
if token != ":":
found_digit = False
while start < lr:
if rev[start] in digits:
num = num * 10 + int(rev[start])
start += 1
found_digit = True
else:
break
# END handle number
# END number parse loop
# no explicit number given, 1 is the default
# It could be 0 though
if not found_digit:
num = 1
# END set default num
# END number parsing only if non-blob mode
parsed_to = start
# handle hiererarchy walk
try:
if token == "~":
obj = to_commit(obj)
for item in xrange(num):
obj = obj.parents[0]
# END for each history item to walk
elif token == "^":
obj = to_commit(obj)
# must be n'th parent
if num:
obj = obj.parents[num - 1]
elif token == ":":
if obj.type != "tree":
obj = obj.tree
# END get tree type
obj = obj[rev[start:]]
parsed_to = lr
else:
raise ValueError("Invalid token: %r" % token)
# END end handle tag
except (IndexError, AttributeError):
raise BadObject("Invalid Revision in %s" % rev)
# END exception handling
# END parse loop
# still no obj ? Its probably a simple name
if obj is None:
obj = name_to_object(repo, rev)
parsed_to = lr
# END handle simple name
if obj is None:
raise ValueError("Revision specifier could not be parsed: %s" % rev)
if parsed_to != lr:
raise ValueError(
"Didn't consume complete rev spec %s, consumed part: %s" %
(rev, rev[:parsed_to]))
return obj
def _sha_to_index(self, sha):
""":return: index for the given sha, or raise"""
index = self._index.sha_to_index(sha)
if index is None:
raise BadObject(sha)
return index
