GH-185: implement rust for CRFFeaturizer (#504)

.github/workflows/release-pypi-core.yml

@@ -0,0 +1,71 @@
+on:
+  push:
+    branches: [ GH-185 ]
+
+jobs:
+  build:
+    name: Build rust
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout master
+        uses: actions/checkout@v1
+      - name: Set up Python 3.6
+        uses: actions/setup-python@v1
+        with:
+          python-version: 3.6
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          curl -sSL https://raw.githubusercontent.com/python-poetry/poetry/master/get-poetry.py | python
+      - name: Add poetry to path
+        run: echo "${HOME}/.poetry/bin" >> $GITHUB_PATH
+      - name: Install package deps
+        working-directory: ./extensions/underthesea_core
+        run: |
+          poetry install
+      - name: Install latest nightly
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly
+          override: true
+      - name: Build Python package
+        working-directory: ./extensions/underthesea_core
+        run: poetry run maturin develop --release
+  pypi-publish:
+    needs: build
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [3.6, 3.7]
+        os: [ubuntu-latest, macos-latest]
+    steps:
+      - uses: actions/checkout@v1
+      - uses: actions/setup-python@v1
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install latest nightly
+        uses: actions-rs/toolchain@v1
+        with:
+          toolchain: nightly
+          override: true
+      - name: Install dependencies
+        working-directory: ./extensions/underthesea_core
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry install
+      - name: Build Python package
+        working-directory: ./extensions/underthesea_core
+        run: poetry run maturin build --release --no-sdist --strip --interpreter python${{ matrix.python-version }}
+      - name: List wheels
+        working-directory: ./extensions/underthesea_core
+        run: find ./target/wheels/
+      - name: Install wheels
+        working-directory: ./extensions/underthesea_core
+        run: pip install target/wheels/underthesea_core*.whl
+      - name: PyPi publish
+        working-directory: ./extensions/underthesea_core
+        env:
+          MATURIN_PASSWORD: ${{ secrets.PYPI_UNDERTHESEA_CORE_API_TOKEN }}
+        run: poetry run maturin publish --username __token__

.github/workflows/release-pypi.yml

@@ -7,24 +7,24 @@ jobs:
     name: Build and package Pypi
     runs-on: ubuntu-latest
     steps:
-        - name: Checkout master
-          uses: actions/checkout@v1
-          with:
-              python-version: 3.6
-        - name: Install pypa/build
-          run: >-
-            python -m
-            pip install
-            build
-            --user
-        - name: Build a binary wheel and a source tarball
-          run: >-
-            python -m
-            build
-            --sdist
-            --wheel
-            --outdir dist/
-        - name: Publish distribution 📦 to PyPI
-          uses: pypa/gh-action-pypi-publish@master
-          with:
-            password: ${{ secrets.PYPI_API_TOKEN }}
+      - name: Checkout master
+        uses: actions/checkout@v1
+        with:
+            python-version: 3.6
+      - name: Install pypa/build
+        run: >-
+          python -m
+          pip install
+          build
+          --user
+      - name: Build a binary wheel and a source tarball
+        run: >-
+          python -m
+          build
+          --sdist
+          --wheel
+          --outdir dist/
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}

extensions/underthesea_core/.gitignore

@@ -0,0 +1 @@
+Cargo.lock

extensions/underthesea_core/Cargo.toml

@@ -0,0 +1,24 @@
+[package]
+name = "underthesea_core"
+version = "0.0.4-alpha.6"
+authors = ["Vu Anh <[email protected]>"]
+description = "Underthesea Core (fast & fun)"
+license = "GPL-3.0"
+edition = "2021"
+readme = "README.md"
+repository = "https://github.com/undertheseanlp/underthesea/"
+homepage = "https://github.com/undertheseanlp/underthesea/"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+serde = { version = "1.0", features = [ "derive" ] }
+regex = "1"
+
+[dependencies.pyo3]
+version = "0.15.0"
+features = ["extension-module"]
+
+[lib]
+name = "underthesea_core"
+crate-type = ["cdylib"]

extensions/underthesea_core/README.md

@@ -0,0 +1 @@
+# Underthesea Core (fast & fun)

extensions/underthesea_core/lab_underthesea_core.py

@@ -0,0 +1,22 @@
+from underthesea_core import CRFFeaturizer
+print("-------------------")
+print("Test underthesea_core")
+
+
+sentences = [
+    [["Chàng", "X"], ["trai", "X"], ["9X", "X"]],
+    [["Khởi", "X"], ["nghiệp", "X"], ["từ", "X"]],
+    [["trường", "X"], ["học", "X"], ["từ", "X"]]
+]
+feature_configs = [
+    "T[0]", "T[1]", "T[2]",
+    "T[0,1].is_in_dict"
+]
+dictionary = set(["Chàng", "trai", "trường học"])
+
+# print("Call featurizer function")
+# print(featurizer(sentences, feature_configs, dictionary))
+
+print("Call CRFFeaturizer function")
+crf_featurizer = CRFFeaturizer(feature_configs, dictionary)
+print(crf_featurizer.process(sentences))

extensions/underthesea_core/pyproject.toml

@@ -0,0 +1,19 @@
+[tool.poetry]
+name = "underthesea_core"
+version = "0.0.4-alpha.6"
+authors = ["Vu Anh <[email protected]>"]
+description = "Underthesea Core (fast & fun)"
+license = "GPL-3.0"
+readme = "README.md"
+repository = "https://github.com/undertheseanlp/underthesea/"
+homepage = "https://github.com/undertheseanlp/underthesea/"
+
+[tool.poetry.dependencies]
+python = "^3.5"
+
+[tool.poetry.dev-dependencies]
+maturin = "==0.9.4"
+
+[build-system]
+requires = ["==0.9.4"]
+build-backend = "maturin"