structo 0.0.1__tar.gz → 0.0.3__tar.gz

structo-0.0.3/.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-0.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: structo
-Version: 0.0.1
+Version: 0.0.3
 Summary: Structify
 Author-email: Ben Brady <benbradybusiness@gmail.com>
 License-Expression: MIT

structo-0.0.3/README.md

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

structo-0.0.3/examples/custom_serializer.py

@@ -0,0 +1,52 @@
+from structo import Serializer
+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]):
+    def write(self, buf, 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]))
+
+    def read(self, buf):
+        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,
+        )
+
+    def sizeof(self):
+        return 1
+
+
+type FlagsDatatype = t.Annotated[Flags, FlagsSerialiser()]
+
+
+value = Flags(
+    flag_a=False,
+    flag_b=True,
+    flag_c=False,
+)
+output = FlagsSerialiser().to_bytes(value)
+print(output)
+print(FlagsSerialiser().from_bytes(output))

structo-0.0.3/examples/iterable_serializer.py

@@ -0,0 +1,64 @@
+import typing as t
+from typing import Annotated
+from structo import (
+    SerializableObject,
+    Serializer,
+    uint32_LE,
+    String,
+    List,
+)
+import random
+from pathlib import Path
+
+
+class Post(SerializableObject):
+    id: Annotated[int, uint32_LE]
+    author: Annotated[str, String(uint32_LE)]
+    tags: Annotated[list[str], List(String(uint32_LE), uint32_LE)]
+
+CONTINUE_BYTE = bytes([255])
+NULL_TERMINATOR = bytes([0])
+
+
+class PostsSerialiser(Serializer[t.Iterable[Post]]):
+    def write(self, buf, value):
+        for item in value:
+            buf.write(CONTINUE_BYTE)
+            item.write(buf)
+
+        buf.write(NULL_TERMINATOR)
+
+    def read(self, buf):
+        while True:
+            continue_byte = buf.read(1)
+            if continue_byte == NULL_TERMINATOR:
+                break
+            assert continue_byte == CONTINUE_BYTE, "Continue byte was not 255"
+
+            print("Loading...")  # to prove it's interspliced loading and yielding
+            yield Post.read(buf)
+
+
+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()
+        PostsSerialiser().write(f, posts)
+
+with open(output, "rb") as f:
+    iterable_posts = PostsSerialiser().read(f)
+    for post in iterable_posts:
+        print(post)

structo-0.0.3/examples/wav.py

@@ -0,0 +1,39 @@
+from typing import Annotated
+from structo import uint16_LE, uint32_LE, SerializableObject, Literal
+
+
+class WavHeader(SerializableObject):
+    chunk_id: Annotated[bytes, Literal(b"RIFF")]
+    chunk_size: Annotated[int, uint32_LE]
+    format: Annotated[bytes, Literal(b"WAVE")]
+
+
+class ChunkHeader(SerializableObject):
+    id: Annotated[bytes, Literal(b"fmt ", b"data")]
+    size: Annotated[int, uint32_LE]
+
+
+class WavFormat(SerializableObject):
+    audio_format: Annotated[int, uint16_LE]
+    num_channels: Annotated[int, uint16_LE]
+    sample_rate: Annotated[int, uint32_LE]
+    byte_range: Annotated[int, uint32_LE]
+    block_align: Annotated[int, uint16_LE]
+    bits_per_sample: Annotated[int, uint16_LE]
+
+
+with open("example.wav", "rb") as f:
+    WavHeader.read(f)
+
+    format_header = ChunkHeader.read(f)
+    assert format_header.id == b'fmt '
+
+    format_data = f.read(format_header.size)
+    format = WavFormat.from_bytes(format_data)
+
+    data_header = ChunkHeader.read(f)
+    assert data_header.id == b"data"
+    wav_data = f.read(data_header.size)
+
+print(format)
+print(len(wav_data))

{structo-0.0.1 → structo-0.0.3}/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-0.0.3/pytest.ini

@@ -0,0 +1,4 @@
+[pytest]
+testpaths =
+    tests
+python_functions = " *"

structo-0.0.3/structo/__init__.py

@@ -0,0 +1,47 @@
+"""
+Structify
+"""
+
+__version__ = "0.0.3"
+
+from .serializer import Serializer
+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,
+    ObjectSerializer,
+)
+from .object import SerializableObject
+from .utils import (
+    StructoReader,
+    StructifyWriter,
+)

structo-0.0.3/structo/object.py

@@ -0,0 +1,58 @@
+import io
+import annotationlib
+import typing as t
+from dataclasses import dataclass
+
+from .serializer import Serializer
+from .serialise import get_serializer
+
+
+class SerializableObjectMeta(type):
+    def __new__(cls, name, bases, dct):
+        new_class = t.cast(type, super().__new__(cls, name, bases, dct))
+        if name == "SerializableObject":
+            return new_class
+
+        annotate = annotationlib.get_annotate_from_class_namespace(dct)
+        _annotations: dict[str, Serializer] = {}
+
+        if annotate:
+            attrs = annotate(annotationlib.Format.VALUE_WITH_FAKE_GLOBALS)
+            for key, value in attrs.items():
+                try:
+                    serializer = get_serializer(value)
+                    _annotations[key] = serializer
+                except Exception as e:
+                    raise ValueError(
+                        f"Invalid attribute defintion for {name}.{key}"
+                    ) from e
+
+        return t.cast(SerializableObject, dataclass(new_class))
+
+
+# This is very messed up since we
+@t.dataclass_transform()
+class SerializableObject(metaclass=SerializableObjectMeta):
+    @classmethod
+    def serializer(cls) -> Serializer[t.Self]:
+        from .types import ObjectSerializer
+
+        return ObjectSerializer(cls)
+
+    @classmethod
+    def sizeof(cls) -> int | None:
+        return cls.serializer().sizeof()
+
+    def write(self, buf: io.Writer):
+        return self.serializer().write(buf, self)
+
+    @classmethod
+    def read(cls, buf: io.Reader) -> t.Self:
+        return cls.serializer().read(buf)
+
+    def to_bytes(self) -> bytes:
+        return self.serializer().to_bytes(self)
+
+    @classmethod
+    def from_bytes(cls, data: bytes) -> t.Self:
+        return cls.serializer().from_bytes(data)

structo-0.0.3/structo/serialise.py

@@ -0,0 +1,41 @@
+import io
+import typing as t
+from .serializer import Serializer
+
+
+def get_serializer(format: type) -> Serializer:
+    from .serializer import Serializer
+    from .object import SerializableObject
+    from .types.object import ObjectSerializer
+
+    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 issubclass(format, SerializableObject):
+        return ObjectSerializer(format)
+
+    # Nicely formatted errors:
+    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}")

structo-0.0.3/structo/serializer.py

@@ -0,0 +1,20 @@
+import io
+
+
+class Serializer[T]:
+    def sizeof(self) -> int | None:
+        return None
+
+    def write(self, buf: io.Writer, value: T): ...
+
+    def read(self, buf: io.Reader) -> T: ...
+
+    def to_bytes(self, value: T) -> bytes:
+        buf = io.BytesIO()
+        self.write(buf, value)
+        buf.seek(0)
+        return buf.getvalue()
+
+    def from_bytes(self, data: bytes) -> T:
+        buf = io.BytesIO(data)
+        return self.read(buf)

structo-0.0.3/structo/types/__init__.py

@@ -0,0 +1,35 @@
+from .primatives 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,
+)
+from .buffer import Buffer
+from .array import Array
+from .blob import Blob
+from .list import List
+from .string import String
+from .literal import Literal
+from .object import ObjectSerializer

structo-0.0.3/structo/types/array.py

@@ -0,0 +1,34 @@
+from ..serializer import Serializer
+
+
+class Array[T](Serializer[list[T]]):
+    length: int
+    type: Serializer[T]
+
+    def __init__(self, length: int, type: Serializer[T]) -> None:
+        assert length > 0, "Array must be longer than 0"
+        self.length = length
+        self.type = type
+
+    def write(self, buf, value):
+        assert (
+            len(value) == self.length
+        ), f"expected array with {self.length} length, receieved {len(value)}"
+
+        for item in value:
+            self.type.write(buf, item)
+
+    def read(self, buf):
+        items = []
+        for _ in range(self.length):
+            items.append(self.type.read(buf))
+
+        return items
+
+    def sizeof(self):
+        element_length = self.type.sizeof()
+        if element_length is None:
+            return None
+        else:
+            return element_length * self.length
+

structo-0.0.3/structo/types/blob.py

@@ -0,0 +1,19 @@
+from ..serializer import Serializer
+
+
+class Blob(Serializer[bytes]):
+    "A set of arbitrary bytes, prefixed with it's length"
+
+    length_type: Serializer[int]
+
+    def __init__(self, length_type: Serializer[int]) -> None:
+        self.length_type = length_type
+
+    def write(self, buf, value):
+        self.length_type.write(buf, len(value))
+        buf.write(value)
+
+    def read(self, buf):
+        length = self.length_type.read(buf)
+        data = buf.read(length)
+        return data

structo-0.0.3/structo/types/buffer.py

@@ -0,0 +1,21 @@
+from ..serializer import Serializer
+
+
+class Buffer(Serializer[bytes]):
+    length: int
+
+    def __init__(self, length: int) -> None:
+        self.length = length
+
+    def write(self, buf, value):
+        assert (
+            len(value) == self.length
+        ), f"expected data with length {self.length}, received {len(value)}"
+        buf.write(value)
+
+    def read(self, buf):
+        data = buf.read(self.length)
+        return data
+
+    def sizeof(self):
+        return self.length