Python: separate compute functions into geoarrow.rust.compute module (

#767)

todo: update docs site

.github/workflows/python-core-wheels.yml

@@ -1,8 +1,11 @@
 # This file is autogenerated by maturin v1.7.1
 # To update, run
 #
-#    maturin generate-ci -m python/geoarrow-core/Cargo.toml --platform all -o tmp.yml github
+#    maturin generate-ci -m python/${{ matrix.module }}/Cargo.toml --platform all -o tmp.yml github
 #
+
+# Wheel builds for Python libraries that are pure-Rust with no complex
+# dependencies (no C dependencies, no http fetching deps)
 name: Python wheels (core)
 
 on:
@@ -32,6 +35,9 @@ jobs:
             target: s390x
           - runner: ubuntu-latest
             target: ppc64le
+        module:
+          - geoarrow-core
+          - geoarrow-compute
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
@@ -41,13 +47,13 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           target: ${{ matrix.platform.target }}
-          args: --release --out dist --manifest-path python/geoarrow-core/Cargo.toml
+          args: --release --out dist --manifest-path python/${{ matrix.module }}/Cargo.toml
           sccache: "true"
           manylinux: auto
       - name: Upload wheels
         uses: actions/upload-artifact@v4
         with:
-          name: wheels-linux-${{ matrix.platform.target }}
+          name: wheels-linux-${{ matrix.platform.target }}-${{ matrix.module }}
           path: dist
 
   musllinux:
@@ -63,6 +69,9 @@ jobs:
             target: aarch64
           - runner: ubuntu-latest
             target: armv7
+        module:
+          - geoarrow-core
+          - geoarrow-compute
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
@@ -72,13 +81,13 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           target: ${{ matrix.platform.target }}
-          args: --release --out dist --manifest-path python/geoarrow-core/Cargo.toml
+          args: --release --out dist --manifest-path python/${{ matrix.module }}/Cargo.toml
           sccache: "true"
           manylinux: musllinux_1_2
       - name: Upload wheels
         uses: actions/upload-artifact@v4
         with:
-          name: wheels-musllinux-${{ matrix.platform.target }}
+          name: wheels-musllinux-${{ matrix.platform.target }}-${{ matrix.module }}
           path: dist
 
   windows:
@@ -90,6 +99,9 @@ jobs:
             target: x64
           - runner: windows-latest
             target: x86
+        module:
+          - geoarrow-core
+          - geoarrow-compute
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
@@ -100,12 +112,12 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           target: ${{ matrix.platform.target }}
-          args: --release --out dist --manifest-path python/geoarrow-core/Cargo.toml
+          args: --release --out dist --manifest-path python/${{ matrix.module }}/Cargo.toml
           sccache: "true"
       - name: Upload wheels
         uses: actions/upload-artifact@v4
         with:
-          name: wheels-windows-${{ matrix.platform.target }}
+          name: wheels-windows-${{ matrix.platform.target }}-${{ matrix.module }}
           path: dist
 
   macos:
@@ -117,6 +129,9 @@ jobs:
             target: x86_64
           - runner: macos-14
             target: aarch64
+        module:
+          - geoarrow-core
+          - geoarrow-compute
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
@@ -126,12 +141,12 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           target: ${{ matrix.platform.target }}
-          args: --release --out dist --manifest-path python/geoarrow-core/Cargo.toml
+          args: --release --out dist --manifest-path python/${{ matrix.module }}/Cargo.toml
           sccache: "true"
       - name: Upload wheels
         uses: actions/upload-artifact@v4
         with:
-          name: wheels-macos-${{ matrix.platform.target }}
+          name: wheels-macos-${{ matrix.platform.target }}-${{ matrix.module }}
           path: dist
 
   emscripten:
@@ -141,6 +156,9 @@ jobs:
         platform:
           - runner: ubuntu-latest
             target: wasm32-unknown-emscripten
+        module:
+          - geoarrow-core
+          - geoarrow-compute
     steps:
       - uses: actions/checkout@v4
       - run: pip install pyodide-build
@@ -162,13 +180,13 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           target: ${{ matrix.platform.target }}
-          args: --release --out dist --no-default-features --manifest-path python/geoarrow-core/Cargo.toml
+          args: --release --out dist --no-default-features --manifest-path python/${{ matrix.module }}/Cargo.toml
           sccache: "true"
           rust-toolchain: nightly
       - name: Upload wheels
         uses: actions/upload-artifact@v4
         with:
-          name: wasm-wheels
+          name: wasm-wheels-${{ matrix.module }}
           path: dist
 
   # sdist:
@@ -179,7 +197,7 @@ jobs:
   #       uses: PyO3/maturin-action@v1
   #       with:
   #         command: sdist
-  #         args: --out dist --manifest-path python/geoarrow-core/Cargo.toml
+  #         args: --out dist --manifest-path python/${{ matrix.module }}/Cargo.toml
   #     - name: Upload sdist
   #       uses: actions/upload-artifact@v4
   #       with:

.github/workflows/python-docs.yml

@@ -58,6 +58,7 @@ jobs:
       - name: Build python package
         run: |
           poetry run maturin develop -m geoarrow-core/Cargo.toml
+          poetry run maturin develop -m geoarrow-compute/Cargo.toml
           poetry run maturin develop -m geoarrow-io/Cargo.toml
 
       - name: Install root project

.github/workflows/python.yml

@@ -143,6 +143,7 @@ jobs:
           # Note: core module should be first, because it could be depended on
           # by others in the future
           poetry run maturin develop -m geoarrow-core/Cargo.toml
+          poetry run maturin develop -m geoarrow-compute/Cargo.toml
           poetry run maturin develop -m geoarrow-io/Cargo.toml
 
       - name: Run python tests

python/Cargo.toml

@@ -1,5 +1,5 @@
 [workspace]
-members = ["geoarrow-core", "geoarrow-io", "pyo3-geoarrow"]
+members = ["geoarrow-compute", "geoarrow-core", "geoarrow-io", "pyo3-geoarrow"]
 resolver = "2"
 
 [workspace.package]

python/DEVELOP.md

@@ -2,6 +2,7 @@
 
 ```
 poetry run maturin develop -m geoarrow-core/Cargo.toml
+poetry run maturin develop -m geoarrow-compute/Cargo.toml
 poetry run maturin develop -m geoarrow-io/Cargo.toml
 poetry run mkdocs serve
 ```
@@ -26,6 +27,7 @@ Then enter into the `python` directory:
 cd python
 poetry install
 poetry run maturin develop -m geoarrow-core/Cargo.toml
+poetry run maturin develop -m geoarrow-compute/Cargo.toml
 poetry run maturin develop -m geoarrow-io/Cargo.toml
 ```
 

python/geoarrow-compute/Cargo.toml

@@ -0,0 +1,38 @@
+[package]
+name = "geoarrow-rust-compute"
+version = { workspace = true }
+authors = { workspace = true }
+edition = { workspace = true }
+description = "Efficient, vectorized geospatial operations in Python."
+readme = "README.md"
+repository = { workspace = true }
+homepage = { workspace = true }
+license = { workspace = true }
+keywords = { workspace = true }
+categories = { workspace = true }
+rust-version = { workspace = true }
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+[lib]
+name = "_compute"
+crate-type = ["cdylib"]
+
+[features]
+default = ["libc", "rayon"]
+libc = ["geoarrow/polylabel"]
+rayon = ["geoarrow/rayon"]
+
+[dependencies]
+arrow = { workspace = true }
+arrow-array = { workspace = true }
+arrow-buffer = { workspace = true }
+pyo3 = { workspace = true }
+pyo3-arrow = { workspace = true }
+pyo3-geoarrow = { path = "../pyo3-geoarrow" }
+geo = "0.28"
+geoarrow = { workspace = true, features = ["geozero"] }
+geozero = { version = "0.13", features = ["with-svg"] }
+numpy = "0.21"
+serde_json = "1"
+thiserror = "1"
+url = "2.5"

python/geoarrow-compute/README.md

@@ -0,0 +1,7 @@
+# `geoarrow.rust.compute`
+
+Compute operations on GeoArrow data.
+
+## Documentation
+
+Refer to the documentation at [geoarrow.org/geoarrow-rs/python](https://geoarrow.org/geoarrow-rs/python).

python/geoarrow-compute/pyproject.toml

@@ -0,0 +1,19 @@
+[build-system]
+requires = ["maturin>=1.4.0,<2.0"]
+build-backend = "maturin"
+
+[project]
+name = "geoarrow-rust-compute"
+requires-python = ">=3.8"
+dependencies = ["arro3-core", "geoarrow-rust-core", "pyproj"]
+classifiers = [
+    "Programming Language :: Rust",
+    "Programming Language :: Python :: Implementation :: CPython",
+    "Programming Language :: Python :: Implementation :: PyPy",
+]
+dynamic = ["version"]
+
+[tool.maturin]
+features = ["pyo3/extension-module"]
+module-name = "geoarrow.rust.compute._compute"
+python-source = "python"

python/geoarrow-compute/python/geoarrow/rust/compute/__init__.py

@@ -0,0 +1,5 @@
+from . import enums
+from ._compute import *
+from ._compute import ___version
+
+__version__: str = ___version()