def stream(self, sha): """For now, all lookup is done by git itself :note: As we don't know when the stream is actually read (and if it is stored for later use) we read the data rigth away and cache it. This has HUGE performance implication, both for memory as for reading/deserializing objects, but we have no other choice in order to make the database behaviour consistent with other implementations !""" hexsha, typename, size, data = self._git.get_object_data(bin_to_hex(sha)) return OStream(hex_to_bin(hexsha), typename, size, StringIO(data))
def store(self, istream): zstream = ZippedStoreShaWriter() self._db.set_ostream(zstream) istream = self._db.store(istream) zstream.close() # close to flush zstream.seek(0) # don't provide a size, the stream is written in object format, hence the # header needs decompression decomp_stream = DecompressMemMapReader(zstream.getvalue(), close_on_deletion=False) self._cache[istream.binsha] = OStream(istream.binsha, istream.type, istream.size, decomp_stream) return istream
def test_streams(self): # test info sha = NULL_BIN_SHA s = 20 blob_id = 3 info = OInfo(sha, str_blob_type, s) assert info.binsha == sha assert info.type == str_blob_type assert info.type_id == blob_id assert info.size == s # test pack info # provides type_id pinfo = OPackInfo(0, blob_id, s) assert pinfo.type == str_blob_type assert pinfo.type_id == blob_id assert pinfo.pack_offset == 0 dpinfo = ODeltaPackInfo(0, blob_id, s, sha) assert dpinfo.type == str_blob_type assert dpinfo.type_id == blob_id assert dpinfo.delta_info == sha assert dpinfo.pack_offset == 0 # test ostream stream = DummyStream() ostream = OStream(*(info + (stream, ))) assert ostream.stream is stream ostream.read(15) stream._assert() assert stream.bytes == 15 ostream.read(20) assert stream.bytes == 20 # test packstream postream = OPackStream(*(pinfo + (stream, ))) assert postream.stream is stream postream.read(10) stream._assert() assert stream.bytes == 10 # test deltapackstream dpostream = ODeltaPackStream(*(dpinfo + (stream, ))) dpostream.stream is stream dpostream.read(5) stream._assert() assert stream.bytes == 5 # derive with own args DeriveTest(sha, str_blob_type, s, stream, 'mine', myarg=3)._assert() # test istream istream = IStream(str_blob_type, s, stream) assert istream.binsha == None istream.binsha = sha assert istream.binsha == sha assert len(istream.binsha) == 20 assert len(istream.hexsha) == 40 assert istream.size == s istream.size = s * 2 istream.size == s * 2 assert istream.type == str_blob_type istream.type = "something" assert istream.type == "something" assert istream.stream is stream istream.stream = None assert istream.stream is None assert istream.error is None istream.error = Exception() assert isinstance(istream.error, Exception)
def stream(self, binsha): type_id, uncomp_data = self._dw_repo.object_store.get_raw(binsha) return OStream(binsha, type_id_to_type_map[type_id], len(uncomp_data), StringIO(uncomp_data))
def stream(self, binsha): type_id, uncomp_data = self._py2_repo.read(binsha) return OStream(binsha, type_id_to_type_map[type_id], len(uncomp_data), StringIO(uncomp_data))
def stream(self, sha): m = self._map_loose_object(sha) type, size, stream = DecompressMemMapReader.new(m, close_on_deletion=True) return OStream(sha, type, size, stream)