PyVortex

PyVortex
--------

The generated documentation for this branch is available at https://spiraldb.github.io/vortex/docs/

The Python package is now structured like this:

- `vortex`
  - `array()`: converts a list or an Arrow array into a Vortex array.
  - `encodings`
    - `Array`: In Rust this is called a PyArray and it is just PyO3 wrapper around a Vortex Rust Array.
      - `to_pandas`
      - `to_numpy`
    - `compress()`: compresses an Array.
  - `dtype`: A module containing dtype constructors, e.g. `uint(32, nullable=False)`
  - `io`: Readers and writers which currently only work for Struct arrays without top-level nulls.
    - `read()`
    - `write()`
  - `expr`
    - `Expr`: a class, implemented in Rust, which constructs vortex-exprs using the obvious Python operators.

I also added `python_repr` which returns a Display-able struct that renders itself in the Python
`repr` style. In particular, the dtypes look like `uint(32, False)` rather than `u32`.

I think the only bugfixes in this PR are:

1. pyvortex/src/encode.rs: propagate the nullability from Arrow to `Array::from_arrow`.
2. arrow/recordbatch.rs and arrow/dtype.rs need to return compatible nullability and validity.

Future Work
-----------

1. Automatically generate and deploy the documentation to github.io.
2. Run `cd pyvortex/docs && make doctest` on every commit.

.gitignore

@@ -72,7 +72,7 @@ instance/
 .scrapy
 
 # Sphinx documentation
-docs/_build/
+pyvortex/docs/_build/
 
 # PyBuilder
 .pybuilder/
@@ -196,3 +196,6 @@ data/
 
 # vscode
 .vscode/
+
+# Emacs
+*~

pyvortex/Cargo.toml

@@ -18,21 +18,29 @@ workspace = true
 [lib]
 name = "pyvortex"
 crate-type = ["rlib", "cdylib"]
+doctest = false
 
 [dependencies]
 arrow = { workspace = true, features = ["pyarrow"] }
+flexbuffers = { workspace = true }
+futures = { workspace = true }
 log = { workspace = true }
 paste = { workspace = true }
 pyo3 = { workspace = true }
 pyo3-log = { workspace = true }
+tokio = { workspace = true, features = ["fs"] }
 vortex-alp = { workspace = true }
 vortex-array = { workspace = true }
 vortex-dict = { workspace = true }
 vortex-dtype = { workspace = true }
 vortex-error = { workspace = true }
+vortex-expr = { workspace = true }
 vortex-fastlanes = { workspace = true }
 vortex-roaring = { workspace = true }
 vortex-runend = { workspace = true }
+vortex-sampling-compressor = { workspace = true }
+vortex-serde = { workspace = true, features = ["tokio"] }
+vortex-scalar = { workspace = true }
 vortex-zigzag = { workspace = true }
 
 # We may need this workaround?

pyvortex/docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?= -W --keep-going
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

pyvortex/docs/conf.py

@@ -0,0 +1,40 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = "Vortex"
+copyright = "2024, Spiral"
+author = "Spiral"
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = [
+    "sphinx.ext.autodoc",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.doctest",
+]
+
+templates_path = ["_templates"]
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
+
+intersphinx_mapping = {
+    "python": ("https://docs.python.org/3", None),
+    "pyarrow": ("https://arrow.apache.org/docs/", None),
+    "pandas": ("https://pandas.pydata.org/docs/", None),
+    "numpy": ("https://numpy.org/doc/stable/", None),
+}
+
+nitpicky = True  # ensures all :class:, :obj:, etc. links are valid
+
+doctest_global_setup = "import pyarrow; import vortex"
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = "pydata_sphinx_theme"
+# html_static_path = ['_static']  # no static files yet

pyvortex/docs/dtype.rst

@@ -0,0 +1,7 @@
+Array Data Types
+================
+
+.. automodule:: vortex.dtype
+   :members:
+   :imported-members:
+

pyvortex/docs/encoding.rst

@@ -0,0 +1,7 @@
+Arrays
+======
+
+.. automodule:: vortex.encoding
+   :members:
+   :imported-members:
+   :special-members: __len__

pyvortex/docs/expr.rst

@@ -0,0 +1,6 @@
+Row Filter Expressions
+======================
+
+.. automodule:: vortex.expr
+   :members:
+   :imported-members:

pyvortex/docs/index.rst

@@ -0,0 +1,19 @@
+.. Vortex documentation master file, created by
+   sphinx-quickstart on Wed Aug 28 10:10:21 2024.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Vortex documentation
+====================
+
+Vortex is an Apache Arrow-compatible toolkit for working with compressed array data.
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+   encoding
+   dtype
+   io
+   expr
+

pyvortex/docs/io.rst

@@ -0,0 +1,6 @@
+Input and Output
+================
+
+.. automodule:: vortex.io
+   :members:
+   :imported-members:

pyvortex/docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

pyvortex/pyproject.toml

@@ -5,7 +5,9 @@ description = "Add your description here"
 authors = [
     { name = "Nicholas Gates", email = "[email protected]" }
 ]
-dependencies = []
+dependencies = [
+    "pydata-sphinx-theme>=0.15.4",
+]
 requires-python = ">= 3.11"
 classifiers = ["Private :: Do Not Upload"]
 
@@ -17,7 +19,10 @@ build-backend = "maturin"
 managed = true
 dev-dependencies = [
     "pyarrow>=15.0.0",
-    "pip"
+    "pip",
+    "sphinx>=8.0.2",
+    "ipython>=8.26.0",
+    "pandas>=2.2.2",
 ]
 
 [tool.maturin]

pyvortex/python/vortex/__init__.py

@@ -1,4 +1,7 @@
-from ._lib import *  # noqa: F403
-from ._lib import __doc__ as module_docs
+from ._lib import __doc__ as module_docs, io, expr, dtype
+from . import encoding
+
 
 __doc__ = module_docs
+del module_docs
+array = encoding.array