Merge pull request #3 from messense/python-binding

Add Python binding

.github/workflows/Python.yml

@@ -0,0 +1,184 @@
+name: Python
+
+on:
+  push:
+  pull_request:
+
+jobs:
+  macos:
+    runs-on: macos-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.6
+          architecture: x64
+      - name: Install Rust toolchain
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          target: aarch64-apple-darwin
+          profile: minimal
+          default: true
+      - name: Install maturin
+        run: pip install maturin
+      - name: Build wheels - x86_64
+        run: |
+          maturin build -i python --target x86_64-apple-darwin --release --out dist -m python/Cargo.toml
+          pip install crfs --no-index --find-links dist --force-reinstall
+          python -c "import crfs"
+      - name: Build wheels - universal2
+        env:
+          DEVELOPER_DIR: /Applications/Xcode.app/Contents/Developer
+          MACOSX_DEPLOYMENT_TARGET: '10.9'
+          PYO3_CROSS_LIB_DIR: /Applications/Xcode.app/Contents/Developer/Library/Frameworks/Python3.framework/Versions/3.8/lib
+        run: |
+          # Build wheels
+          maturin build -i python --release --universal2 --out dist --no-sdist -m python/Cargo.toml
+          pip install crfs --no-index --find-links dist --force-reinstall
+          python -c "import crfs"
+      - name: Upload wheels
+        uses: actions/upload-artifact@v2
+        with:
+          name: wheels
+          path: dist
+
+  windows:
+    runs-on: windows-latest
+    strategy:
+      matrix:
+        platform: [
+          { python-architecture: "x64", target: "x86_64-pc-windows-msvc" },
+          { python-architecture: "x86", target: "i686-pc-windows-msvc" },
+        ]
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.6
+          architecture: ${{ matrix.platform.python-architecture }}
+      - name: Install Rust toolchain
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: stable
+          target: ${{ matrix.platform.target }}
+          profile: minimal
+          default: true
+      - name: Install maturin
+        run: pip install maturin
+      - name: Build wheels
+        run: |
+          maturin build -i python --release --out dist --no-sdist -m python/Cargo.toml --target ${{ matrix.platform.target }}
+          pip install crfs --no-index --find-links dist --force-reinstall
+          python -c "import crfs"
+      - name: Upload wheels
+        uses: actions/upload-artifact@v2
+        with:
+          name: wheels
+          path: dist
+
+  linux:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        platform: [
+          { manylinux: '2010', target: "x86_64-unknown-linux-gnu", arch: "x86_64" },
+          { manylinux: '2010', target: "i686-unknown-linux-gnu", arch: "i686" },
+        ]
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+      with:
+        python-version: 3.6
+        architecture: x64
+    - name: Build Wheels
+      run: |
+        echo 'curl --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
+        source ~/.cargo/env
+        export PATH=/opt/python/cp38-cp38/bin:$PATH
+        pip install maturin
+        maturin build -i python --release --out dist --no-sdist -m python/Cargo.toml --target ${{ matrix.platform.target }} --manylinux ${{ matrix.platform.manylinux }}
+        pip install crfs --no-index --find-links dist --force-reinstall
+        python -c "import crfs"
+        ' > build-wheel.sh
+
+        docker run --rm -v "$PWD":/io -w /io quay.io/pypa/manylinux${{ matrix.platform.manylinux }}_${{ matrix.platform.arch }} bash build-wheel.sh
+    - name: Auditwheel Symbols
+      run: |
+        pip install auditwheel-symbols
+        auditwheel-symbols dist/*.whl
+    - name: Upload wheels
+      uses: actions/upload-artifact@v2
+      with:
+        name: wheels
+        path: dist
+
+  linux-cross:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        platform: [
+          { manylinux: "2014", target: "aarch64-unknown-linux-gnu", arch: "aarch64" },
+          { manylinux: "2014", target: "armv7-unknown-linux-gnueabihf", arch: "armv7" },
+        ]
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+      with:
+        python-version: 3.6
+    - name: Build Wheels
+      run: |
+        echo 'curl -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable
+        source ~/.cargo/env
+        rustup target add ${{ matrix.platform.target }}
+        maturin build -i python --release --out dist --no-sdist -m python/Cargo.toml --target ${{ matrix.platform.target }} --manylinux ${{ matrix.platform.manylinux }}
+        ' > build-wheel.sh
+
+        docker run --rm -v "$PWD":/io -w /io messense/manylinux2014-cross:${{ matrix.platform.arch }} bash build-wheel.sh
+    - uses: uraimo/[email protected]
+      name: Install built wheel
+      with:
+        arch: ${{ matrix.platform.arch }}
+        distro: ubuntu18.04
+        githubToken: ${{ github.token }}
+        # Mount the dist directory as /artifacts in the container
+        dockerRunArgs: |
+          --volume "${PWD}/dist:/artifacts"
+        install: |
+          apt-get update
+          apt-get install -y --no-install-recommends python3 python3-pip
+          pip3 install -U pip
+        run: |
+          ls -lrth /artifacts
+          pip3 install crfs --no-index --find-links /artifacts --force-reinstall
+          python3 -c "import crfs"
+    - name: Auditwheel Symbols
+      run: |
+        pip install auditwheel-symbols
+        auditwheel-symbols dist/*.whl
+    - name: Upload wheels
+      uses: actions/upload-artifact@v2
+      with:
+        name: wheels
+        path: dist
+
+
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    if: "startsWith(github.ref, 'refs/tags/')"
+    needs: [ macos, windows, linux, linux-cross ]
+    steps:
+      - uses: actions/download-artifact@v2
+        with:
+          name: wheels
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+      - name: Publish to PyPi
+        env:
+          TWINE_USERNAME: __token__
+          TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+        run: |
+          pip install --upgrade wheel pip setuptools twine
+          twine upload --skip-existing *

.gitignore

@@ -1,3 +1,4 @@
 /target
+/python/target
 Cargo.lock
 tests/output/*.cqdb

python/.cargo/config.toml

@@ -0,0 +1,11 @@
+[target.x86_64-apple-darwin]
+rustflags = [
+  "-C", "link-arg=-undefined",
+  "-C", "link-arg=dynamic_lookup",
+]
+
+[target.aarch64-apple-darwin]
+rustflags = [
+  "-C", "link-arg=-undefined",
+  "-C", "link-arg=dynamic_lookup",
+]

python/Cargo.toml

@@ -0,0 +1,24 @@
+[package]
+name = "py-crfs"
+version = "0.1.0"
+authors = ["messense <[email protected]>"]
+edition = "2018"
+license = "MIT"
+keywords = ["crf", "crfsuite"]
+readme = "README.md"
+homepage = "https://github.com/messense/crfs-rs"
+repository = "https://github.com/messense/crfs-rs.git"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[lib]
+name = "crfs"
+crate-type = ["cdylib"]
+
+[dependencies]
+crfs-rs = { package = "crfs", version = "0.1.0" }
+ouroboros = "0.8.2"
+pyo3 = { version = "0.13.2", features = ["abi3-py36", "extension-module"] }
+
+[package.metadata.maturin]
+name = "crfs"

python/src/lib.rs

@@ -0,0 +1,94 @@
+use std::fs;
+
+use crfs_rs::{Attribute, Model};
+use ouroboros::self_referencing;
+use pyo3::prelude::*;
+
+#[pyclass(module = "crfs", name = "Attribute")]
+#[derive(FromPyObject)]
+struct PyAttribute {
+    /// Attribute name
+    #[pyo3(get, set)]
+    name: String,
+    /// Value of the attribute
+    #[pyo3(get, set)]
+    value: f64,
+}
+
+#[pymethods]
+impl PyAttribute {
+    #[new]
+    fn new(name: String, value: f64) -> Self {
+        Self { name, value }
+    }
+}
+
+#[derive(FromPyObject)]
+enum PyAttributeInput {
+    #[pyo3(transparent)]
+    Attr(PyAttribute),
+    Dict {
+        /// Attribute name
+        #[pyo3(item("name"))]
+        name: String,
+        /// Value of the attribute
+        #[pyo3(item("value"))]
+        value: f64,
+    },
+    Tuple(String, f64),
+}
+
+impl From<PyAttributeInput> for Attribute {
+    fn from(attr: PyAttributeInput) -> Self {
+        match attr {
+            PyAttributeInput::Attr(PyAttribute { name, value }) => Attribute::new(name, value),
+            PyAttributeInput::Dict { name, value } => Attribute::new(name, value),
+            PyAttributeInput::Tuple(name, value) => Attribute::new(name, value),
+        }
+    }
+}
+
+#[pyclass(module = "crfs", name = "Model")]
+#[self_referencing]
+struct PyModel {
+    data: Vec<u8>,
+    #[borrows(data)]
+    #[not_covariant]
+    model: Model<'this>,
+}
+
+#[pymethods]
+impl PyModel {
+    #[new]
+    fn new_py(data: Vec<u8>) -> PyResult<Self> {
+        let model = PyModelTryBuilder {
+            data,
+            model_builder: |model_data| Model::new(model_data),
+        }
+        .try_build()?;
+        Ok(model)
+    }
+
+    #[staticmethod]
+    fn open(path: &str) -> PyResult<Self> {
+        let data = fs::read(path)?;
+        Self::new_py(data)
+    }
+
+    pub fn tag(&self, xseq: Vec<Vec<PyAttributeInput>>) -> PyResult<Vec<String>> {
+        let mut tagger = self.with_model(|model| model.tagger())?;
+        let xseq: Vec<Vec<Attribute>> = xseq
+            .into_iter()
+            .map(|xs| xs.into_iter().map(Into::into).collect())
+            .collect();
+        let labels = tagger.tag(&xseq)?;
+        Ok(labels.iter().map(|l| l.to_string()).collect())
+    }
+}
+
+#[pymodule]
+fn crfs(_py: Python, m: &PyModule) -> PyResult<()> {
+    m.add_class::<PyAttribute>()?;
+    m.add_class::<PyModel>()?;
+    Ok(())
+}