ormsgpack 1.4.0__tar.gz → 1.4.1__tar.gz

{ormsgpack-1.4.0 → ormsgpack-1.4.1}/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 1.4.1 12/11/2023
+
+### Fixed
+
+- Fix performance regression in dict serialization introduced in 1.3.0
+
 ## 1.4.0 05/11/2023
 
 ### Fixed

{ormsgpack-1.4.0 → ormsgpack-1.4.1}/Cargo.lock

@@ -118,7 +118,7 @@ checksum = "dd8b5dd2ae5ed71462c540258bedcb51965123ad7e7ccf4b9a8cafaa4a63576d"
 
 [[package]]
 name = "ormsgpack"
-version = "1.4.0"
+version = "1.4.1"
 dependencies = [
  "ahash",
  "associative-cache",
@@ -266,9 +266,9 @@ checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
 
 [[package]]
 name = "serde"
-version = "1.0.190"
+version = "1.0.192"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91d3c334ca1ee894a2c6f6ad698fe8c435b76d504b13d436f0685d648d6d96f7"
+checksum = "bca2a08484b285dcb282d0f67b26cadc0df8b19f8c12502c13d966bf9482f001"
 dependencies = [
  "serde_derive",
 ]
@@ -284,9 +284,9 @@ dependencies = [
 
 [[package]]
 name = "serde_derive"
-version = "1.0.190"
+version = "1.0.192"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67c5609f394e5c2bd7fc51efda478004ea80ef42fee983d5c67a65e34f32c0e3"
+checksum = "d6c7207fbec9faa48073f3e3074cbe553af6ea512d7c21ba46e434e70ea9fbc1"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -301,9 +301,9 @@ checksum = "f27f6278552951f1f2b8cf9da965d10969b2efdea95a6ec47987ab46edfe263a"
 
 [[package]]
 name = "smallvec"
-version = "1.11.1"
+version = "1.11.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "942b4a808e05215192e39f4ab80813e599068285906cc91aa64f923db842bd5a"
+checksum = "4dccd0940a2dcdf68d092b8cbab7dc0ad8fa938bf95787e1b916b0e3d0e8e970"
 
 [[package]]
 name = "syn"

{ormsgpack-1.4.0 → ormsgpack-1.4.1}/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "ormsgpack"
-version = "1.4.0"
+version = "1.4.1"
 authors = [
     "Aviram Hassan <aviramyhassan@gmail.com>",
     "Emanuele Giaquinta <emanuele.giaquinta@gmail.com>",
@@ -49,7 +49,7 @@ rmp-serde = { version = "1", default_features = false }
 serde = { version = "1", default_features = false }
 serde_bytes = { version = "0.11.12", default_features = false, features = ["std"] }
 simdutf8 = { version = "0.1", default_features = false, features = ["std", "aarch64_neon"] }
-smallvec = { version = "^1.8", default_features = false, features = ["union", "write"] }
+smallvec = { version = "^1.11", default_features = false, features = ["union", "write"] }
 
 [build-dependencies]
 pyo3-build-config = { version = "^0.20.0" }

{ormsgpack-1.4.0 → ormsgpack-1.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ormsgpack
-Version: 1.4.0
+Version: 1.4.1
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
@@ -146,7 +146,7 @@ The global interpreter lock (GIL) is held for the duration of the call.
 
 It raises `MsgpackEncodeError` on an unsupported type. This exception message
 describes the invalid object with the error message
-`Type is not JSON serializable: ...`. To fix this, specify
+`Type is not msgpack serializable: ...`. To fix this, specify
 [default](#default).
 
 It raises `MsgpackEncodeError` on a `str` that contains invalid UTF-8.
@@ -162,8 +162,7 @@ It raises `MsgpackEncodeError` on circular references.
 It raises `MsgpackEncodeError`  if a `tzinfo` on a datetime object is
 unsupported.
 
-`MsgpackEncodeError` is a subclass of `TypeError`. This is for compatibility
-with the standard library.
+`MsgpackEncodeError` is a subclass of `TypeError`.
 
 #### default
 
@@ -181,7 +180,7 @@ def default(obj):
     raise TypeError
 
 >>> ormsgpack.packb(decimal.Decimal("0.0842389659712649442845"))
-MsgpackEncodeError: Type is not JSON serializable: decimal.Decimal
+MsgpackEncodeError: Type is not msgpack serializable: decimal.Decimal
 >>> ormsgpack.packb(decimal.Decimal("0.0842389659712649442845"), default=default)
 b'\xb80.0842389659712649442845'
 >>> ormsgpack.packb({1, 2}, default=default)
@@ -252,9 +251,7 @@ has no effect on `datetime.datetime` objects that have `tzinfo` set.
 
 Serialize `dict` keys of type other than `str`. This allows `dict` keys
 to be one of `str`, `int`, `float`, `bool`, `None`, `datetime.datetime`,
-`datetime.date`, `datetime.time`, `enum.Enum`, and `uuid.UUID`. For comparison,
-the standard library serializes `str`, `int`, `float`, `bool` or `None` by
-default.
+`datetime.date`, `datetime.time`, `enum.Enum`, and `uuid.UUID`.
 
 ```python
 >>> import ormsgpack, datetime, uuid
@@ -435,8 +432,7 @@ Serialize `pydantic.BaseModel` instances.
 ##### OPT_SORT_KEYS
 
 Serialize `dict` keys in sorted order. The default is to serialize in an
-unspecified order. This is equivalent to `sort_keys=True` in the standard
-library.
+unspecified order.
 
 This can be used to ensure the order is deterministic for hashing or tests.
 It has a substantial performance penalty and is not recommended in general.
@@ -457,8 +453,6 @@ The sorting is not collation/locale-aware:
 b'\x83\xa1A\x03\xa1a\x01\xa2\xc3\xa4\x02'
 ```
 
-This is the same sorting behavior as the standard library.
-
 `dataclass` also serialize as maps but this has no effect on them.
 
 ##### OPT_UTC_Z
@@ -585,7 +579,7 @@ test_dataclass_msgpack       140.2774 (40.96)    143.6087 (18.42)    141.3847 (3
 
 ormsgpack serializes `datetime.datetime` objects to
 [RFC 3339](https://tools.ietf.org/html/rfc3339) format,
-e.g., "1970-01-01T00:00:00+00:00". This is a subset of ISO 8601 and
+e.g., "1970-01-01T00:00:00+00:00". This is a subset of ISO 8601 and is
 compatible with `isoformat()` in the standard library.
 
 ```python
@@ -632,17 +626,13 @@ module, or a timezone instance from the third-party `pendulum`, `pytz`, or
 
 Errors with `tzinfo` result in `MsgpackEncodeError` being raised.
 
-It is faster to have ormsgpack serialize datetime objects than to do so
-before calling `packb()`. If using an unsupported type such as
-`pendulum.datetime`, use `default`.
-
 To disable serialization of `datetime` objects specify the option
 `ormsgpack.OPT_PASSTHROUGH_DATETIME`.
 
 To use "Z" suffix instead of "+00:00" to indicate UTC ("Zulu") time, use the option
 `ormsgpack.OPT_UTC_Z`.
 
-To assume datetimes without timezone are UTC, se the option `ormsgpack.OPT_NAIVE_UTC`.
+To assume datetimes without timezone are UTC, use the option `ormsgpack.OPT_NAIVE_UTC`.
 
 ### enum
 

{ormsgpack-1.4.0 → ormsgpack-1.4.1}/README.md

@@ -114,7 +114,7 @@ The global interpreter lock (GIL) is held for the duration of the call.
 
 It raises `MsgpackEncodeError` on an unsupported type. This exception message
 describes the invalid object with the error message
-`Type is not JSON serializable: ...`. To fix this, specify
+`Type is not msgpack serializable: ...`. To fix this, specify
 [default](#default).
 
 It raises `MsgpackEncodeError` on a `str` that contains invalid UTF-8.
@@ -130,8 +130,7 @@ It raises `MsgpackEncodeError` on circular references.
 It raises `MsgpackEncodeError`  if a `tzinfo` on a datetime object is
 unsupported.
 
-`MsgpackEncodeError` is a subclass of `TypeError`. This is for compatibility
-with the standard library.
+`MsgpackEncodeError` is a subclass of `TypeError`.
 
 #### default
 
@@ -149,7 +148,7 @@ def default(obj):
     raise TypeError
 
 >>> ormsgpack.packb(decimal.Decimal("0.0842389659712649442845"))
-MsgpackEncodeError: Type is not JSON serializable: decimal.Decimal
+MsgpackEncodeError: Type is not msgpack serializable: decimal.Decimal
 >>> ormsgpack.packb(decimal.Decimal("0.0842389659712649442845"), default=default)
 b'\xb80.0842389659712649442845'
 >>> ormsgpack.packb({1, 2}, default=default)
@@ -220,9 +219,7 @@ has no effect on `datetime.datetime` objects that have `tzinfo` set.
 
 Serialize `dict` keys of type other than `str`. This allows `dict` keys
 to be one of `str`, `int`, `float`, `bool`, `None`, `datetime.datetime`,
-`datetime.date`, `datetime.time`, `enum.Enum`, and `uuid.UUID`. For comparison,
-the standard library serializes `str`, `int`, `float`, `bool` or `None` by
-default.
+`datetime.date`, `datetime.time`, `enum.Enum`, and `uuid.UUID`.
 
 ```python
 >>> import ormsgpack, datetime, uuid
@@ -403,8 +400,7 @@ Serialize `pydantic.BaseModel` instances.
 ##### OPT_SORT_KEYS
 
 Serialize `dict` keys in sorted order. The default is to serialize in an
-unspecified order. This is equivalent to `sort_keys=True` in the standard
-library.
+unspecified order.
 
 This can be used to ensure the order is deterministic for hashing or tests.
 It has a substantial performance penalty and is not recommended in general.
@@ -425,8 +421,6 @@ The sorting is not collation/locale-aware:
 b'\x83\xa1A\x03\xa1a\x01\xa2\xc3\xa4\x02'
 ```
 
-This is the same sorting behavior as the standard library.
-
 `dataclass` also serialize as maps but this has no effect on them.
 
 ##### OPT_UTC_Z
@@ -553,7 +547,7 @@ test_dataclass_msgpack       140.2774 (40.96)    143.6087 (18.42)    141.3847 (3
 
 ormsgpack serializes `datetime.datetime` objects to
 [RFC 3339](https://tools.ietf.org/html/rfc3339) format,
-e.g., "1970-01-01T00:00:00+00:00". This is a subset of ISO 8601 and
+e.g., "1970-01-01T00:00:00+00:00". This is a subset of ISO 8601 and is
 compatible with `isoformat()` in the standard library.
 
 ```python
@@ -600,17 +594,13 @@ module, or a timezone instance from the third-party `pendulum`, `pytz`, or
 
 Errors with `tzinfo` result in `MsgpackEncodeError` being raised.
 
-It is faster to have ormsgpack serialize datetime objects than to do so
-before calling `packb()`. If using an unsupported type such as
-`pendulum.datetime`, use `default`.
-
 To disable serialization of `datetime` objects specify the option
 `ormsgpack.OPT_PASSTHROUGH_DATETIME`.
 
 To use "Z" suffix instead of "+00:00" to indicate UTC ("Zulu") time, use the option
 `ormsgpack.OPT_UTC_Z`.
 
-To assume datetimes without timezone are UTC, se the option `ormsgpack.OPT_NAIVE_UTC`.
+To assume datetimes without timezone are UTC, use the option `ormsgpack.OPT_NAIVE_UTC`.
 
 ### enum
 

{ormsgpack-1.4.0 → ormsgpack-1.4.1}/src/serialize/dict.rs

@@ -111,7 +111,8 @@ impl Serialize for Dict {
     where
         S: Serializer,
     {
-        let mut map = serializer.serialize_map(None).unwrap();
+        let len = ffi!(Py_SIZE(self.ptr)) as usize;
+        let mut map = serializer.serialize_map(Some(len)).unwrap();
         for (key, value) in PyDictIter::from_pyobject(self.ptr) {
             if unlikely!(!is_type!(ob_type!(key.as_ptr()), STR_TYPE)) {
                 err!(KEY_MUST_BE_STR)
@@ -182,7 +183,7 @@ impl Serialize for DictSortedKey {
 
         items.sort_unstable_by(|a, b| a.0.cmp(b.0));
 
-        let mut map = serializer.serialize_map(None).unwrap();
+        let mut map = serializer.serialize_map(Some(len)).unwrap();
         for (key, val) in items.iter() {
             let pyvalue = PyObjectSerializer::new(
                 *val,
@@ -231,7 +232,8 @@ impl Serialize for DictNonStrKey {
         S: Serializer,
     {
         let opts = self.opts & NOT_PASSTHROUGH;
-        let mut map = serializer.serialize_map(None).unwrap();
+        let len = ffi!(Py_SIZE(self.ptr)) as usize;
+        let mut map = serializer.serialize_map(Some(len)).unwrap();
         for (key, value) in PyDictIter::from_pyobject(self.ptr) {
             if is_type!(ob_type!(key.as_ptr()), STR_TYPE) {
                 let data = unicode_to_str(key.as_ptr());