Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: speed up unpacking arrays #257

Merged
merged 2 commits into from
Sep 27, 2023
Merged

feat: speed up unpacking arrays #257

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f8009c9
feat: speed up unpacking arrays
bdraco Sep 27, 2023
7d257b9
feat: cleanup
bdraco Sep 27, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 13 additions & 4 deletions src/dbus_fast/_private/unmarshaller.pxd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,14 +76,21 @@ cdef SignatureType SIGNATURE_TREE_A_QV_TYPES_0
cdef SignatureTree SIGNATURE_TREE_A_OA_SA_SV
cdef SignatureType SIGNATURE_TREE_A_OA_SA_SV_TYPES_0

cdef unsigned int TOKEN_B_AS_INT
cdef unsigned int TOKEN_U_AS_INT
cdef unsigned int TOKEN_Y_AS_INT
cdef unsigned int TOKEN_A_AS_INT
cdef unsigned int TOKEN_O_AS_INT
cdef unsigned int TOKEN_S_AS_INT
cdef unsigned int TOKEN_G_AS_INT
cdef unsigned int TOKEN_N_AS_INT
cdef unsigned int TOKEN_A_AS_INT
cdef unsigned int TOKEN_B_AS_INT
cdef unsigned int TOKEN_U_AS_INT
cdef unsigned int TOKEN_Y_AS_INT
cdef unsigned int TOKEN_X_AS_INT
cdef unsigned int TOKEN_T_AS_INT
cdef unsigned int TOKEN_D_AS_INT
cdef unsigned int TOKEN_Q_AS_INT
cdef unsigned int TOKEN_V_AS_INT
cdef unsigned int TOKEN_LEFT_CURLY_AS_INT
cdef unsigned int TOKEN_LEFT_PAREN_AS_INT

cdef object MARSHALL_STREAM_END_ERROR
cdef object DEFAULT_BUFFER_SIZE
Expand Down Expand Up @@ -189,9 +196,11 @@ cdef class Unmarshaller:
@cython.locals(
beginning_pos=cython.ulong,
array_length=cython.uint,
children=cython.list,
child_type=SignatureType,
child_0=SignatureType,
child_1=SignatureType,
token_as_int=cython.uint,
)
cpdef object read_array(self, SignatureType type_)

Expand Down
51 changes: 37 additions & 14 deletions src/dbus_fast/_private/unmarshaller.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,14 @@
TOKEN_S_AS_INT = ord("s")
TOKEN_G_AS_INT = ord("g")
TOKEN_N_AS_INT = ord("n")
TOKEN_X_AS_INT = ord("x")
TOKEN_T_AS_INT = ord("t")
TOKEN_D_AS_INT = ord("d")
TOKEN_Q_AS_INT = ord("q")
TOKEN_V_AS_INT = ord("v")
TOKEN_LEFT_CURLY_AS_INT = ord("{")
TOKEN_LEFT_PAREN_AS_INT = ord("(")


ARRAY = array.array
SOL_SOCKET = socket.SOL_SOCKET
Expand Down Expand Up @@ -513,46 +521,61 @@ def read_array(self, type_: _SignatureType) -> Iterable[Any]:
else:
array_length = self._uint32_unpack(self._buf, self._pos - UINT32_SIZE)[0] # type: ignore[misc]

child_type = type_.children[0]
token = child_type.token
child_type: SignatureType = type_.children[0]
token_as_int = ord(child_type.token[0])

if token in "xtd{(":
if (
token_as_int == TOKEN_X_AS_INT
or token_as_int == TOKEN_T_AS_INT
or token_as_int == TOKEN_D_AS_INT
or token_as_int == TOKEN_LEFT_CURLY_AS_INT
or token_as_int == TOKEN_LEFT_PAREN_AS_INT
):
# the first alignment is not included in the array size
self._pos += -self._pos & 7 # align 8

if token == "y":
if token_as_int == TOKEN_Y_AS_INT:
self._pos += array_length
return self._buf[self._pos - array_length : self._pos]

if token == "{":
if token_as_int == TOKEN_LEFT_CURLY_AS_INT:
result_dict: Dict[Any, Any] = {}
beginning_pos = self._pos
children = child_type.children
child_0 = children[0]
child_1 = children[1]
child_0_token = child_0.token
child_1_token = child_1.token
child_0_token_as_int = ord(child_0.token[0])
child_1_token_as_int = ord(child_1.token[0])
# Strings with variant values are the most common case
# so we optimize for that by inlining the string reading
# and the variant reading here
if child_0_token in "os" and child_1_token == "v":
if (
child_0_token_as_int == TOKEN_O_AS_INT
or child_0_token_as_int == TOKEN_S_AS_INT
) and child_1_token_as_int == TOKEN_V_AS_INT:
while self._pos - beginning_pos < array_length:
self._pos += -self._pos & 7 # align 8
key: Union[str, int] = self._read_string_unpack()
result_dict[key] = self._read_variant()
elif child_0_token == "q" and child_1_token == "v":
elif (
child_0_token_as_int == TOKEN_Q_AS_INT
and child_1_token_as_int == TOKEN_V_AS_INT
):
while self._pos - beginning_pos < array_length:
self._pos += -self._pos & 7 # align 8
key = self._read_uint16_unpack()
result_dict[key] = self._read_variant()
elif child_0_token in "os" and child_1_token == "a":
if (
child_0_token_as_int == TOKEN_O_AS_INT
or child_0_token_as_int == TOKEN_S_AS_INT
) and child_1_token_as_int == TOKEN_A_AS_INT:
while self._pos - beginning_pos < array_length:
self._pos += -self._pos & 7 # align 8
key = self._read_string_unpack()
result_dict[key] = self.read_array(child_1)
else:
reader_1 = self._readers[child_1_token]
reader_0 = self._readers[child_0_token]
reader_1 = self._readers[child_1.token]
reader_0 = self._readers[child_0.token]
while self._pos - beginning_pos < array_length:
self._pos += -self._pos & 7 # align 8
key = reader_0(self, child_0)
Expand All @@ -565,11 +588,11 @@ def read_array(self, type_: _SignatureType) -> Iterable[Any]:

result_list = []
beginning_pos = self._pos
if token in "os":
if token_as_int == TOKEN_O_AS_INT or token_as_int == TOKEN_S_AS_INT:
while self._pos - beginning_pos < array_length:
result_list.append(self._read_string_unpack())
return result_list
reader = self._readers[token]
reader = self._readers[child_type.token]
while self._pos - beginning_pos < array_length:
result_list.append(reader(self, child_type))
return result_list
Expand Down
5 changes: 4 additions & 1 deletion src/dbus_fast/signature.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,16 +24,19 @@ class to parse signatures.
__slots__ = ("token", "children", "_signature")

def __init__(self, token: str) -> None:
self.token = token
"""Init a new SignatureType."""
self.token: str = token
self.children: List[SignatureType] = []
self._signature: Optional[str] = None

def __eq__(self, other: Any) -> bool:
"""Compare this type to another type or signature string."""
if type(other) is SignatureType:
return self.signature == other.signature
return super().__eq__(other)

def _collapse(self) -> str:
"""Collapse this type into a signature string."""
if self.token not in "a({":
return self.token

Expand Down
Loading