create python directory

.cargo/config

@@ -0,0 +1,5 @@
+[target.x86_64-apple-darwin]
+rustflags = [
+  "-C", "link-arg=-undefined",
+  "-C", "link-arg=dynamic_lookup",
+]

Cargo.toml

@@ -12,4 +12,4 @@ unicode-normalization = "0.1.8"
 [dev-dependencies]
 itertools = "0.8.2"
 quickcheck = "0.8"
-quickcheck_macros = "0.8"
+quickcheck_macros = "0.8"

python/.gitignore

@@ -0,0 +1,128 @@
+### https://raw.github.com/github/gitignore/499ae899e7b54e701e878759f73d9092302fd07a/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+

python/Cargo.toml

@@ -0,0 +1,19 @@
+[package]
+name = "python"
+version = "0.1.0"
+authors = ["Yohei Tamura <[email protected]>"]
+edition = "2018"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+tokenizations = { path = ".." }
+
+
+[lib]
+name = "tokenizations"
+crate-type = ["cdylib"]
+
+[dependencies.pyo3]
+version = "0.8.4"
+features = ["extension-module"]

python/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["maturin"]
+build-backend = "maturin"

python/requirements-dev.txt

@@ -0,0 +1,3 @@
+pytest
+hypothesis
+black

python/src/lib.rs

@@ -0,0 +1,17 @@
+use pyo3::prelude::*;
+use pyo3::wrap_pyfunction;
+use tokenizations::{get_alignments, Alignment};
+
+#[pymodule]
+fn tokenizations(py: Python, m: &PyModule) -> PyResult<()> {
+    #[pyfn(m, "get_alignments")]
+    pub fn get_alignments_py(
+        _py: Python,
+        a: Vec<&str>,
+        b: Vec<&str>,
+    ) -> PyResult<(Alignment, Alignment)> {
+        Ok(get_alignments(&a, &b))
+    }
+
+    Ok(())
+}

src/lib.rs

@@ -8,6 +8,8 @@ extern crate unicode_normalization;
 use std::collections::HashMap;
 use unicode_normalization::UnicodeNormalization;
 
+pub type Alignment = Vec<Vec<usize>>;
+
 fn normalize(text: &str) -> String {
     text.nfkd().collect()
 }
@@ -204,8 +206,6 @@ fn get_alignment(
     at2bt
 }
 
-type Alignment = Vec<Vec<usize>>;
-
 pub fn get_alignments(a: &[&str], b: &[&str]) -> (Alignment, Alignment) {
     let a: Vec<String> = a.iter().map(|x| normalize(*x)).collect();
     let b: Vec<String> = b.iter().map(|x| normalize(*x)).collect();