Merge branch 'release/v0.0.2a0'

.github/workflows/build-publish.yaml

@@ -6,7 +6,6 @@ on:
       - main
   workflow_dispatch:
 
-
 jobs:
   build_and_test:
     name: Test
@@ -24,8 +23,8 @@ jobs:
   macos:
     runs-on: macos-latest
     strategy:
-      matrix: 
-        python-version: [ '3.7', '3.8', '3.9']
+      matrix:
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - uses: actions/checkout@v3
       - uses: actions/setup-python@v4
@@ -47,77 +46,76 @@ jobs:
           name: wheels
           path: dist
 
-
   linux:
     runs-on: ubuntu-latest
     strategy:
       matrix:
         target: [x86_64]
-        python-version: [ '3.7', '3.8', '3.9']
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
-    - uses: actions/checkout@v3
-    - uses: actions/setup-python@v4
-      with:
-        python-version: ${{ matrix.python-version }}
-        architecture: x64
-    - name: Build source wheels
-      uses: PyO3/maturin-action@v1
-      with:
-        target: ${{ matrix.target }}
-        manylinux: auto
-        args: --release --out dist --sdist -m Cargo.toml -i ${{ matrix.python-version }}
-    - name: Build wheels
-      uses: PyO3/maturin-action@v1
-      with:
-        target: ${{ matrix.target }}
-        manylinux: auto
-        args: --release --out dist -m Cargo.toml -i ${{ matrix.python-version }}
-    - name: Install built wheel
-      if: matrix.target == 'x86_64'
-      run: |
-        pip install texy --no-index --find-links dist --force-reinstall
-        python -c "import texy"
-    - name: Upload wheels
-      uses: actions/upload-artifact@v3
-      with:
-        name: wheels
-        path: dist
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+      - name: Build source wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          manylinux: auto
+          args: --release --out dist --sdist -m Cargo.toml -i ${{ matrix.python-version }}
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          manylinux: auto
+          args: --release --out dist -m Cargo.toml -i ${{ matrix.python-version }}
+      - name: Install built wheel
+        if: matrix.target == 'x86_64'
+        run: |
+          pip install texy --no-index --find-links dist --force-reinstall
+          python -c "import texy"
+      - name: Upload wheels
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
 
   musllinux:
     runs-on: ubuntu-latest
     strategy:
       matrix:
         target:
           - x86_64-unknown-linux-musl
-        python-version: [ '3.7', '3.8', '3.9']
+        python-version: ["3.7", "3.8", "3.9"]
     steps:
-    - uses: actions/checkout@v3
-    - uses: actions/setup-python@v4
-      with:
-        python-version: ${{ matrix.python-version }}
-        architecture: x64
-    - name: Build wheels
-      uses: PyO3/maturin-action@v1
-      with:
-        target: ${{ matrix.target }}
-        manylinux: musllinux_1_2
-        args: --release --out dist -m Cargo.toml -i ${{ matrix.python-version }}
-    - name: Install built wheel
-      if: matrix.target == 'x86_64-unknown-linux-musl'
-      uses: addnab/docker-run-action@v3
-      with:
-        image: alpine:latest
-        options: -v ${{ github.workspace }}:/io -w /io
-        run: |
-          apk add py3-pip
-          pip3 install -U pip
-          pip3 install texy --no-index --find-links /io/dist/ --force-reinstall
-          python3 -c "import texy"
-    - name: Upload wheels
-      uses: actions/upload-artifact@v3
-      with:
-        name: wheels
-        path: dist
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.target }}
+          manylinux: musllinux_1_2
+          args: --release --out dist -m Cargo.toml -i ${{ matrix.python-version }}
+      - name: Install built wheel
+        if: matrix.target == 'x86_64-unknown-linux-musl'
+        uses: addnab/docker-run-action@v3
+        with:
+          image: alpine:latest
+          options: -v ${{ github.workspace }}:/io -w /io
+          run: |
+            apk add py3-pip
+            pip3 install -U pip
+            pip3 install texy --no-index --find-links /io/dist/ --force-reinstall
+            python3 -c "import texy"
+      - name: Upload wheels
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
 
   musllinux-cross:
     runs-on: ubuntu-latest
@@ -128,41 +126,41 @@ jobs:
             arch: aarch64
           - target: armv7-unknown-linux-musleabihf
             arch: armv7
-        python-version: [ '3.7', '3.8', '3.9']
+        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
-    - uses: actions/checkout@v3
-    - uses: actions/setup-python@v4
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Build wheels
-      uses: PyO3/maturin-action@v1
-      with:
-        target: ${{ matrix.platform.target }}
-        manylinux: musllinux_1_2
-        args: --release --out dist -m Cargo.toml -i ${{ matrix.python-version }}
-    - uses: uraimo/[email protected]
-      name: Install built wheel
-      with:
-        arch: ${{ matrix.platform.arch }}
-        distro: alpine_latest
-        githubToken: ${{ github.token }}
-        install: |
-          apk add py3-pip
-          pip3 install -U pip
-        run: |
-          pip3 install texy --no-index --find-links dist/ --force-reinstall
-          python3 -c "import texy"
-    - name: Upload wheels
-      uses: actions/upload-artifact@v3
-      with:
-        name: wheels
-        path: dist
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          manylinux: musllinux_1_2
+          args: --release --out dist -m Cargo.toml -i ${{ matrix.python-version }}
+      - uses: uraimo/[email protected]
+        name: Install built wheel
+        with:
+          arch: ${{ matrix.platform.arch }}
+          distro: alpine_latest
+          githubToken: ${{ github.token }}
+          install: |
+            apk add py3-pip
+            pip3 install -U pip
+          run: |
+            pip3 install texy --no-index --find-links dist/ --force-reinstall
+            python3 -c "import texy"
+      - name: Upload wheels
+        uses: actions/upload-artifact@v3
+        with:
+          name: wheels
+          path: dist
 
   release:
     name: Release
     runs-on: ubuntu-latest
     # if: "startsWith(github.ref, 'refs/tags/')"
-    needs: [ macos, linux, musllinux, musllinux-cross]
+    needs: [macos, linux, musllinux, musllinux-cross]
     steps:
       - uses: actions/download-artifact@v3
         with:
@@ -173,4 +171,4 @@ jobs:
         uses: PyO3/maturin-action@v1
         with:
           command: upload
-          args: --skip-existing *
+          args: --skip-existing *

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "texy-process"
-version = "0.0.1-alpha2"
+version = "0.0.2-alpha"
 edition = "2021"
 
 [lib]
@@ -9,15 +9,16 @@ crate-type = ["cdylib", "rlib"]
 
 [dependencies]
 regex = "1.7.0"
-pyo3 = { version = "0.17.3", features = ["abi3-py37", "extension-module"] }
 lazy_static = "1.4.0"
 serde_json = "1.0.89"
 rayon = "1.6.1"
 procspawn = "0.10.1"
 
+[dependencies.pyo3]
+version = "0.19.0"
+features = ["abi3-py37"]
+
 [features]
 extension-module = ["pyo3/extension-module"]
 default = ["extension-module"]
 
-[package.metadata.maturin]
-name = "texy._internal"

Makefile

@@ -0,0 +1,30 @@
+.SHELL := /bin/bash
+.PHONY: all format lint test test-rs build-dev build-release
+
+all: lint format test test-rs
+	@echo "All done!"
+
+format:
+	@echo "Running formatter..."
+	isort .
+	black .
+
+lint:
+	@echo "Running linter..."
+	-ruff . --fix
+
+test:
+	@echo "Running tests..."
+	-pytest -vs tests/
+
+test-rs:
+	@echo "Running tests..."
+	-cargo test -- --nocapture
+
+build-dev:
+	@echo "Building dev..."
+	-maturin develop
+
+build-release:
+	@echo "Building release..."
+	-maturin build --release

README.md

@@ -4,15 +4,45 @@
 
 [![Python](https://github.com/mdmmn378/texy/actions/workflows/build-publish.yaml/badge.svg)](https://github.com/mdmmn378/texy/actions/workflows/build-publish.yaml)
 
-> Do text processing without getting your hands dirty
+> A utility library for quickly cleaning texts
 
 ## Installation
 
-> `pip install texy`
+Python version in the dev environment: `3.11.5`
 
-## Example:
+> `pip install -U texy`
 
-```py
-from texy.pipelines import run_101
-run_101(["💩🔙🙈🚘🚺🦷🦨🧒🏻🫸🕑🐠🧷🍈🐟🐡🦈🐬  <hello>what's up</hello>,"])
+## Usage
+
+Pipelines with parallelization in Rust:
+
+```python
+>>> from texy.pipelines import extreme_clean, strict_clean, relaxed_clean
+>>> data = ["hello ;/ from the other side 😊 \t "]
+print(extreme_clean(data))
+>>> ['hello from the other side']
+print(strict_clean(data))
+>>> ['hello ;/ from the other side']
+print(relaxed_clean(data))
+>>> ['hello ;/ from the other side 😊']
 ```
+
+Parallelize custom functions with Python Multiprocessing:
+
+```python
+from texy.pipelines import parallelize
+
+def dummy(x):
+    return [i[0] for i in x]
+
+data = ["a ", "b ", "c ", "d ", "e ", "f ", "g ", "h ?."] * 100
+print(parallelize(dummy, data, 2))
+```
+
+## Actions
+
+| Pipeline        | Actions                                                                                                                                                               |
+| --------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `relaxed_clean` | `remove_newlines`, `remove_html`, `remove_xml`, `merge_spaces`                                                                                                        |
+| `strict_clean`  | `remove_newlines`, `remove_urls`, `remove_emails`, `remove_html`, `remove_xml`, `remove_emoticons`, `remove_emojis`, `remove_infrequent_punctuations`, `merge_spaces` |
+| `extreme_clean` | `remove_newlines`, `remove_urls`, `remove_emails`, `remove_html`, `remove_xml`, `remove_emoticons`, `remove_emojis`, `remove_all_punctuations`, `merge_spaces`        |

pyproject.toml

@@ -3,7 +3,7 @@ name = "texy"
 description = "Supercharge text processing"
 readme = "README.md"
 requires-python = ">=3.6"
-version = "0.0.1-alpha2"
+version = "0.0.2-alpha"
 authors = [
   { name="Mamunur Rahaman Mamun", email="[email protected]" },
 ]
@@ -13,8 +13,11 @@ homepage = "https://github.com/mdmmn378/texy"
 repository = "https://github.com/mdmmn378/texy"
 
 [build-system]
-requires = ["maturin>=0.14,<0.15"]
+requires = ["maturin>=1.0.0,<=2.0.0"]
 build-backend = "maturin"
 
+[tool.maturin]
+features = ["pyo3/extension-module"]
+
 [tool.isort]
 profile = "black"