lazyscribe-arrow 0.1.0__py3-none-any.whl

lazyscribe_arrow/__init__.py

@@ -0,0 +1,5 @@
+"""Import the custom artifact handlers."""
+
+from lazyscribe_arrow.csv import CSVArtifact
+
+__all__: list[str] = ["CSVArtifact"]

lazyscribe_arrow/_meta.py

@@ -0,0 +1,3 @@
+"""Version."""
+
+__version__ = "0.1.0"

lazyscribe_arrow/csv.py

@@ -0,0 +1,101 @@
+"""Custom artifact handlers for CSVs."""
+
+import logging
+from datetime import datetime
+from typing import Any, ClassVar
+
+import pyarrow as pa
+from attrs import define
+from lazyscribe._utils import utcnow
+from lazyscribe.artifacts.base import Artifact
+from pyarrow import csv
+from slugify import slugify
+
+LOG = logging.getLogger(__name__)
+
+
+@define(auto_attribs=True)
+class CSVArtifact(Artifact):
+    """Arrow-powered CSV handler."""
+
+    alias: ClassVar[str] = "csv"
+    suffix: ClassVar[str] = "csv"
+    binary: ClassVar[bool] = True
+    output_only: ClassVar[bool] = False
+
+    @classmethod
+    def construct(
+        cls,
+        name: str,
+        value: Any | None = None,
+        fname: str | None = None,
+        created_at: datetime | None = None,
+        writer_kwargs: dict | None = None,
+        version: int = 0,
+        dirty: bool = True,
+        **kwargs,
+    ):
+        """Construct the handler class."""
+        created_at = created_at or utcnow()
+
+        return cls(  # type: ignore[call-arg]
+            name=name,
+            value=value,
+            fname=fname
+            or f"{slugify(name)}-{slugify(created_at.strftime('%Y%m%d%H%M%S'))}.{cls.suffix}",
+            writer_kwargs=writer_kwargs or {},
+            version=version,
+            created_at=created_at,
+            dirty=dirty,
+        )
+
+    @classmethod
+    def read(cls, buf, **kwargs) -> pa.Table:
+        """Read in the CSV file.
+
+        Parameters
+        ----------
+        buf : file-like object
+            The buffer from a ``fsspec`` filesystem.
+        **kwargs
+            Keyword arguments for the read method.
+
+        Returns
+        -------
+        pyarrow.lib.Table
+            A ``pyarrow`` table with the data.
+        """
+        return csv.read_csv(buf, **kwargs)
+
+    @classmethod
+    def write(cls, obj, buf, **kwargs):
+        """Write the CSV file using pyarrow.
+
+        Parameters
+        ----------
+        obj : object
+            The object to write.
+        buf : file-like object
+            The buffer from a ``fsspec`` filesystem.
+        **kwargs
+            Keyword arguments for :py:meth:`pyarrow.csv.write_csv`.
+
+        Raises
+        ------
+        ValueError
+            Raised if the supplied object does not have ``__arrow_c_array__``
+            or ``__arrow_c_stream__`` attributes. These attributes allow us to
+            perform a zero-copy transformation from the native obejct to a PyArrow
+            Table.
+        """
+        if isinstance(obj, pa.Table):
+            LOG.debug("Provided object is already a PyArrow table.")
+        elif hasattr(obj, "__arrow_c_array__") or hasattr(obj, "__arrow_c_stream__"):
+            obj = pa.table(obj)
+        else:
+            raise ValueError(
+                f"Object of type `{type(obj)}` cannot be easily coerced into a PyArrow Table. "
+                "Please provide an object that implements the Arrow PyCapsule Interface."
+            )
+
+        csv.write_csv(obj, buf, **kwargs)

lazyscribe_arrow-0.1.0.dist-info/METADATA

@@ -0,0 +1,44 @@
+Metadata-Version: 2.4
+Name: lazyscribe-arrow
+Version: 0.1.0
+Summary: Arrow-based artifact handlers for Lazyscribe
+Author-email: Akshay Gupta <akgcodes@gmail.com>
+License: MIT license
+Project-URL: Documentation, https://github.com/lazyscribe/lazyscribe-arrow
+Project-URL: Repository, https://github.com/lazyscribe/lazyscribe-arrow
+Classifier: Development Status :: 3 - Alpha
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10.0
+Description-Content-Type: text/markdown
+Requires-Dist: attrs<=25.1.0,>=21.2.0
+Requires-Dist: lazyscribe<=1.1.0,>=1.0.0
+Requires-Dist: pyarrow<=19.0.1,>=14.0.1
+Requires-Dist: python-slugify<=8.0.4,>=5.0.0
+Provides-Extra: build
+Requires-Dist: build; extra == "build"
+Requires-Dist: commitizen; extra == "build"
+Requires-Dist: twine; extra == "build"
+Requires-Dist: wheel; extra == "build"
+Provides-Extra: qa
+Requires-Dist: edgetest; extra == "qa"
+Requires-Dist: mypy; extra == "qa"
+Requires-Dist: pre-commit; extra == "qa"
+Requires-Dist: ruff; extra == "qa"
+Requires-Dist: types-python-slugify; extra == "qa"
+Requires-Dist: uv; extra == "qa"
+Provides-Extra: tests
+Requires-Dist: pandas; extra == "tests"
+Requires-Dist: pytest; extra == "tests"
+Requires-Dist: pytest-cov; extra == "tests"
+Requires-Dist: time-machine; extra == "tests"
+Provides-Extra: dev
+Requires-Dist: lazyscribe-arrow[build]; extra == "dev"
+Requires-Dist: lazyscribe-arrow[qa]; extra == "dev"
+Requires-Dist: lazyscribe-arrow[tests]; extra == "dev"

lazyscribe_arrow-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+lazyscribe_arrow/__init__.py,sha256=nZR8SxoxZjsGSVwdMFTI9l582H0M-77iec3NXzCeziU,127
+lazyscribe_arrow/_meta.py,sha256=FT4J4aKqWfsY7SJy-yg7R1ebCnARJzh_OZjkyUpF0NQ,38
+lazyscribe_arrow/csv.py,sha256=mFgYkntabK65KDguS5wuWe3vd7IG0dznKi01EEGf5QY,2972
+lazyscribe_arrow-0.1.0.dist-info/METADATA,sha256=7IcYyuWzrkgeRsxJVH-Erz0fYb-Kaxy7lQZbCf7T6rQ,1813
+lazyscribe_arrow-0.1.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+lazyscribe_arrow-0.1.0.dist-info/entry_points.txt,sha256=4ymVC3yTTvMs2iOibuw9pt7goZ0zWWhgdjJ6NzMS_cw,62
+lazyscribe_arrow-0.1.0.dist-info/top_level.txt,sha256=C_ElBcqIKkSjUmMQPDECDhhP54M7muep1KLnEiFJ61I,17
+lazyscribe_arrow-0.1.0.dist-info/RECORD,,

lazyscribe_arrow-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (78.1.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

lazyscribe_arrow-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[lazyscribe.artifact_type]
+csv = lazyscribe_arrow:CSVArtifact

lazyscribe_arrow-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+lazyscribe_arrow