structo 0.0.1__tar.gz → 0.0.2__tar.gz

structo-0.0.2/.gitignore

@@ -0,0 +1,217 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+output.raw

{structo-0.0.1 → structo-0.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: structo
-Version: 0.0.1
+Version: 0.0.2
 Summary: Structify
 Author-email: Ben Brady <benbradybusiness@gmail.com>
 License-Expression: MIT

structo-0.0.2/README.md

@@ -0,0 +1,11 @@
+# Structo
+
+```py
+
+```
+
+## Examples
+
+See ./examples for example usage
+
+

structo-0.0.2/examples/custom_serializer.py

@@ -0,0 +1,54 @@
+from structo import Serializer, serialize_to_bytes, deserialize_from_bytes
+from dataclasses import dataclass
+import typing as t
+
+# We don't inherit from SerialiableObject
+# since we're using a custom serializer
+@dataclass
+class Flags:
+    flag_a: bool
+    flag_b: bool
+    flag_c: bool
+
+class FlagsSerialiser(Serializer[Flags]):
+    # This is optional, but allows for size calculations
+    @staticmethod
+    def length(format):
+        return 1
+
+    @staticmethod
+    def write(buf, format, value):
+        byte = 0
+        if value.flag_a:
+            byte += 1 << 0
+        if value.flag_b:
+            byte += 1 << 1
+        if value.flag_c:
+            byte += 1 << 2
+
+        byte = buf.write(bytes([byte]))
+
+    @staticmethod
+    def read(buf, format):
+        byte = buf.read(1)[0]
+        flag_a = ((byte >> 0) & 1) != 0
+        flag_b = ((byte >> 1) & 1) != 0
+        flag_c = ((byte >> 2) & 1) != 0
+        return Flags(
+            flag_a=flag_a,
+            flag_b=flag_b,
+            flag_c=flag_c,
+        )
+
+type FlagsDatatype = t.Annotated[Flags, FlagsSerialiser]
+
+
+value = Flags(
+    flag_a=False,
+    flag_b=True,
+    flag_c=False,
+)
+output = serialize_to_bytes(flags_datatype, value)
+print(output)
+print(deserialize_from_bytes(flags_datatype, output))
+

structo-0.0.2/examples/iterable_serializer.py

@@ -0,0 +1,64 @@
+from structo import (
+    SerializableObject,
+    Serializer,
+    write_serializable,
+    read_serializable,
+    uint32_LE,
+    String,
+    List,
+)
+import random
+import typing as t
+from pathlib import Path
+
+
+class Post(SerializableObject):
+    id: uint32_LE
+    author: String[uint32_LE]
+    tags: List[uint32_LE, String[uint32_LE]]
+
+
+class PostsSerialiser(Serializer[t.Iterable[Post]]):
+    @staticmethod
+    def write(buf, format, value):
+        for item in value:
+            buf.write(bytes([255]))
+            write_serializable(buf, Post, item)
+
+        buf.write(bytes([0]))
+
+    @staticmethod
+    def read(buf, format):
+        while True:
+            continue_byte = buf.read(1)[0]
+            if continue_byte == 0:
+                break
+            assert continue_byte == 255, "Continue byte was not 255"
+
+            print("Loading...")  # to prove it's interspliced loading and yielding
+            yield read_serializable(buf, Post)
+
+
+type PostsIterable = t.Annotated[t.Iterable[Post], PostsSerialiser()]
+
+
+# Too large to effectively store in memory
+def generate_posts():
+    for x in range(1_000_000):
+        yield Post(
+            id=random.randint(0, 1_000_000),
+            author="Me",
+            tags=[str(random.randint(0, 100)) for _ in range(random.randint(0, 10))],
+        )
+
+
+output = Path("output.raw")
+if not output.exists():
+    with open(output, "wb") as f:
+        posts = generate_posts()
+        write_serializable(f, PostsIterable, posts)
+
+with open(output, "rb") as f:
+    iterable_posts = read_serializable(f, PostsIterable)
+    for post in iterable_posts:
+        print(post)

structo-0.0.2/examples/wav.py

@@ -0,0 +1,40 @@
+from structo import uint16_LE, uint32_LE, SerializableObject, Literal
+
+
+class RiffHeader(SerializableObject):
+    chunk_id: Literal[b"RIFF"]
+    chunk_size: uint32_LE
+    format: Literal[b"WAVE"]
+
+
+class FormatChunkHeader(SerializableObject):
+    id: Literal[b"fmt "]
+    size: uint32_LE
+
+
+class DataChunkHeader(SerializableObject):
+    id: Literal[b"data"]
+    size: uint32_LE
+
+
+class WavFormat(SerializableObject):
+    audio_format: uint16_LE
+    num_channels: uint16_LE
+    sample_rate: uint32_LE
+    byte_range: uint32_LE
+    block_align: uint16_LE
+    bits_per_sample: uint16_LE
+
+
+with open("example.wav", "rb") as f:
+    RiffHeader.read(f)
+
+    format_header = FormatChunkHeader.read(f)
+    format_data = f.read(format_header.size)
+    format = WavFormat.from_bytes(format_data)
+
+    data_header = DataChunkHeader.read(f)
+    wav_data = f.read(data_header.size)
+
+print(format)
+print(len(wav_data))

{structo-0.0.1 → structo-0.0.2}/pyproject.toml

@@ -11,3 +11,9 @@ dynamic = ["version", "description"]
 
 [project.urls]
 Home = "https://nnilky.site"
+
+[dependency-groups]
+dev = [
+    "black>=26.1.0",
+    "pytest>=9.0.2",
+]

structo-0.0.2/structo/__init__.py

@@ -0,0 +1,49 @@
+"""
+Structify
+"""
+
+__version__ = "0.0.2"
+
+from .object import SerializableObject
+from .serialise import write_serializable, read_serializable
+from .serializer import Serializer, Format
+from .types import (
+    uint64_BE,
+    uint64_LE,
+    uint64,
+    uint32_BE,
+    uint32_LE,
+    uint32,
+    uint16_BE,
+    uint16_LE,
+    uint16,
+    uint8,
+    int64_BE,
+    int64_LE,
+    int64,
+    int32_BE,
+    int32_LE,
+    int32,
+    int16_BE,
+    int16_LE,
+    int16,
+    int8,
+    float64_BE,
+    float64_LE,
+    float64,
+    float32_BE,
+    float32_LE,
+    float32,
+    Array,
+    Buffer,
+    List,
+    String,
+    Blob,
+    Literal
+)
+from .utils import (
+    StructoReader,
+    StructifyWriter,
+    serialize_to_bytes,
+    deserialize_from_bytes,
+)

structo-0.0.2/structo/object.py

@@ -0,0 +1,48 @@
+import typing as t
+import io
+from dataclasses import dataclass
+import annotationlib
+
+
+class SerializableObjectMeta(type):
+    def __new__(cls, name, bases, dct):
+        from .serialise import get_serializer
+
+        new_class = super().__new__(cls, name, bases, dct)
+        annotate = annotationlib.get_annotate_from_class_namespace(dct)
+        if annotate:
+            attrs = annotate(annotationlib.Format.VALUE_WITH_FAKE_GLOBALS)
+            for key, value in attrs.items():
+                try:
+                    get_serializer(value)
+                except Exception as e:
+                    raise ValueError(
+                        f"Invalid attribute defintion for {name}.{key}"
+                    ) from e
+
+        return dataclass(new_class)  # type: ignore
+
+
+@t.dataclass_transform()
+class SerializableObject(metaclass=SerializableObjectMeta):
+    @classmethod
+    def read(cls, buf: io.Reader) -> t.Self:
+        from .serialise import read_serializable
+
+        return read_serializable(buf, cls)
+
+    def write(self, buf: io.Writer):
+        from .serialise import write_serializable
+
+        write_serializable(buf, type(self), self)
+
+    @classmethod
+    def from_bytes(cls, data: bytes) -> t.Self:
+        buf = io.BytesIO(data)
+        return cls.read(buf)
+
+    def to_bytes(self) -> bytes:
+        buf = io.BytesIO()
+        self.write(buf)
+        buf.seek(0)
+        return buf.read()

structo-0.0.2/structo/serialise.py

@@ -0,0 +1,77 @@
+import io
+import typing as t
+import annotationlib
+from .serializer import Format, Serializer
+
+
+def get_serializer(format: Format) -> Serializer:
+    from .object import SerializableObject
+
+    class SerialiableObjectSerializer(Serializer):
+        @staticmethod
+        def write(buf: io.Writer, format: type, value: SerializableObject):
+            annotations = annotationlib.get_annotations(format)
+            for field_key, field_format in annotations.items():
+                field_value = getattr(value, field_key)
+                write_serializable(buf, field_format, field_value)
+
+        @staticmethod
+        def read(buf: io.Reader, format: type) -> SerializableObject:
+            annotations = annotationlib.get_annotations(format)
+            attrs = {}
+            for field_key, field_format in annotations.items():
+                field_value = read_serializable(buf, field_format)
+                attrs[field_key] = field_value
+
+            return format(**attrs)
+
+    if hasattr(format, "__value__"):
+        format = format.__value__
+
+    if t.get_origin(format) is t.Annotated:
+        args = t.get_args(format)
+        serializers = [arg for arg in args if isinstance(arg, Serializer)]
+        assert len(serializers) != 0, f"No serializers for {format} found"
+        assert len(serializers) == 1, f"More than one serializers for {format} found"
+        serializer = serializers[0]
+
+        return serializer
+
+    if isinstance(format, type) and issubclass(format, SerializableObject):
+        return SerialiableObjectSerializer()
+
+    if format == int:
+        raise ValueError(
+            f"No serializer for int, you need to use structo.int32, structo.int32 or similar instead"
+        )
+    if format == float:
+        raise ValueError(
+            f"No serializer for float, you need to use structo.float32 or structo.float64 instead"
+        )
+    if format == bytes:
+        raise ValueError(
+            f"No serializer for bytes, you need to use structo.Buffer or structo.Blob instead"
+        )
+    if format == list:
+        raise ValueError(
+            f"No serializer for list, you need to use structo.List or structo.Array instead"
+        )
+
+    raise NotImplementedError(f"No serializer found for {format}")
+
+
+def write_serializable(buf: io.Writer, format: Format, value: t.Any):
+    return get_serializer(format).write(buf, format, value)
+
+
+def read_serializable(buf: io.Reader, format: Format) -> t.Any:
+    return get_serializer(format).read(buf, format)
+
+
+def read_uint(buf: io.Reader, format: Format) -> int:
+    value = read_serializable(buf, format)
+
+    assert isinstance(value, int), f"expected uint, got {format}"
+    assert value >= 0, "expected uint, got {format}"
+
+    return value

structo-0.0.2/structo/serializer.py

@@ -0,0 +1,13 @@
+import typing as t
+import io
+
+type Format = type | t.TypeAliasType
+
+
+class Serializer[T]:
+    def length(self, format: Format) -> int | None:
+        return None
+
+    def write(self, buf: io.Writer, format: Format, value: T): ...
+
+    def read(self, buf: io.Reader, format: Format) -> T: ...

structo-0.0.2/structo/tests/test_primatives.py

@@ -0,0 +1,105 @@
+import typing as t
+from dataclasses import dataclass
+
+import pytest
+import structo as st
+from structo import (
+    SerializableObject,
+    deserialize_from_bytes,
+    uint16,
+    uint16_LE,
+    uint16_BE,
+    serialize_to_bytes,
+)
+from utils import assert_serialises_correctly, assert_equal
+
+
+testdata: list[tuple[st.Format, t.Any, bytes]] = []
+
+
+@dataclass
+class EncodeTests[T]:
+    datatype: st.Format
+    tests: list[tuple[T, bytes]]
+
+
+testdata.append((st.Literal[b"foo"], b"foo", b"foo"))
+
+testsets: list[EncodeTests] = [
+    EncodeTests(
+        datatype=st.uint8,
+        tests=[
+            (1, bytes([1])),
+            (100, bytes([100])),
+            (255, bytes([255])),
+        ],
+    ),
+    EncodeTests(
+        datatype=st.Literal,
+        tests=[
+            (1, bytes([1])),
+            (100, bytes([100])),
+            (255, bytes([255])),
+        ],
+    ),
+]
+
+for testset in testsets:
+    for value, expected in testset.tests:
+        testdata.append((testset.datatype, value, expected))
+
+
+@dataclass
+class BinaryEncodeTests[T]:
+    tests: list[tuple[T, bytes]]
+    le: st.Format
+    be: st.Format
+    be_default: st.Format
+
+
+binary_testsets: list[BinaryEncodeTests] = [
+    BinaryEncodeTests(
+        le=st.uint16_LE,
+        be=st.uint16_BE,
+        be_default=st.uint16,
+        tests=[
+            (1, bytes([0, 1])),
+            ((256 * 2) + 1, bytes([2, 1])),
+        ],
+    ),
+    BinaryEncodeTests(
+        le=st.uint32_LE,
+        be=st.uint32_BE,
+        be_default=st.uint32,
+        tests=[
+            (1, bytes([0, 0, 0, 1])),
+            ((2 << 8) + 1, bytes([0, 0, 2, 1])),
+            ((3 << 16) + (2 << 8) + 1, bytes([0, 3, 2, 1])),
+            ((4 << 24) + (3 << 16) + (2 << 8) + 1, bytes([4, 3, 2, 1])),
+        ],
+    ),
+    BinaryEncodeTests(
+        le=st.uint64_LE,
+        be=st.uint64_BE,
+        be_default=st.uint64,
+        tests=[
+            (1, bytes([0, 0, 0, 0, 0, 0, 0, 1])),
+            ((3 << 16) + (2 << 8) + 1, bytes([0, 0, 0, 0, 3, 2, 1])),
+            ((1 << 48) + 1, bytes([1, 0, 0, 0, 0, 0, 0, 1])),
+        ],
+    ),
+]
+
+for testset in binary_testsets:
+    for value, expected in testset.tests:
+        testdata.append((testset.be, value, expected))
+        testdata.append((testset.be_default, value, expected))
+        testdata.append((testset.le, value, bytes(reversed(expected))))
+
+
+@pytest.mark.parametrize("datatype,value,expected", testdata)
+def test_encode_primitives(datatype, value, expected):
+    actual = serialize_to_bytes(datatype, value)
+    assert (
+        actual == expected
+    ), f"{datatype} {value=} | expected {expected}, recieved {actual}"