Merge pull request #68 from bact/add-license-spdx-in-bindings

Add license header to bindings
PyThaiNLP · Nov 9, 2024 · 96d9c27 · 96d9c27
2 parents c5b81ca + ef6af04
commit 96d9c27
Show file tree

Hide file tree

Showing 21 changed files with 146 additions and 57 deletions.
diff --git a/CITATION.cff b/CITATION.cff
@@ -26,5 +26,5 @@ keywords:
   - "Thai language"
   - "Thai NLP"
 license: Apache-2.0
-version: v1.3.2
-date-released: "2021-07-17"
+version: v1.4.0
+date-released: "2024-11-09"
diff --git a/Cargo.toml b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "nlpo3"
-version = "1.3.2"
+version = "1.4.0"
 edition = "2018"
 license = "Apache-2.0"
 authors = ["Thanathip Suntorntip Gorlph"]

diff --git a/README.md b/README.md
@@ -44,7 +44,7 @@ pip install nlpo3
     or from `Vec<String>`
 
 [tcc]: https://dl.acm.org/doi/10.1145/355214.355225
-[benchmark]: https://github.com/PyThaiNLP/nlpo3/blob/main/nlpo3-python/notebooks/nlpo3_segment_benchmarks.ipynb
+[benchmark]: ./nlpo3-python/notebooks/nlpo3_segment_benchmarks.ipynb
 
 ## Dictionary file
 
@@ -110,7 +110,7 @@ In `Cargo.toml`:
 ```toml
 [dependencies]
 # ...
-nlpo3 = "1.3.2"
+nlpo3 = "1.4.0"
 ```
 
 #### Example

diff --git a/nlpo3-cli/Cargo.toml b/nlpo3-cli/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "nlpo3-cli"
-version = "0.2.0"
+version = "0.2.1-dev"
 edition = "2018"
 authors = ["Vee Satayamas <[email protected]>"]
 description = "Command line interface for nlpO3, a Thai natural language processing library"
@@ -18,4 +18,4 @@ path = "src/main.rs"
 
 [dependencies]
 clap = { version = "3.0.0-beta.2" }
-nlpo3 = { version = "1.2.0" }
+nlpo3 = { version = "1.4.0" }
diff --git a/nlpo3-cli/README.md b/nlpo3-cli/README.md
@@ -1,8 +1,13 @@
-<a href="https://crates.io/crates/nlpo3-cli/"><img alt="crates.io" src="https://img.shields.io/crates/v/nlpo3-cli.svg"/></a>
-<a href="https://opensource.org/licenses/Apache-2.0"><img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"/></a>
+---
+SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+SPDX-License-Identifier: Apache-2.0
+---
 
 # nlpo3-cli
 
+[![crates.io](https://img.shields.io/crates/v/nlpo3-cli.svg "crates.io")](https://crates.io/crates/nlpo3-cli/)
+[![Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg "Apache-2.0")](https://opensource.org/licenses/Apache-2.0)
+
 Command line interface for nlpO3, a Thai natural language processing library.
 
 ## Install

diff --git a/nlpo3-cli/src/main.rs b/nlpo3-cli/src/main.rs
@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+// SPDX-License-Identifier: Apache-2.0
+
 use clap::Clap;
 use nlpo3::tokenizer::newmm_custom::Newmm;
 use nlpo3::tokenizer::tokenizer_trait::Tokenizer;

diff --git a/nlpo3-nodejs/Cargo.toml b/nlpo3-nodejs/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "nlpo3-nodejs"
-version = "0.3.0"
+version = "1.0.0"
 edition = "2018"
 license = "Apache-2.0"
 authors = ["Thanathip Suntorntip Gorlph"]
@@ -10,11 +10,11 @@ exclude = ["index.node"]
 crate-type = ["cdylib"]
 
 [dependencies]
-ahash = "0.7.6"
-lazy_static = "1.4.0"
-nlpo3 = "1.3.2"
+ahash = "0.8.6"
+lazy_static = "1.5.0"
+nlpo3 = "1.4.0"
 
 [dependencies.neon]
-version = "0.8"
+version = "0.22.6"
 default-features = false
 features = ["napi-6"]
diff --git a/nlpo3-nodejs/README.md b/nlpo3-nodejs/README.md
@@ -1,15 +1,23 @@
-<a href="https://opensource.org/licenses/Apache-2.0"><img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"/></a>
+---
+SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+SPDX-License-Identifier: Apache-2.0
+---
 
 # nlpO3 Node.js binding
 
+[![Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg "Apache-2.0")](https://opensource.org/licenses/Apache-2.0)
+
 Node.js binding for nlpO3, a Thai natural language processing library in Rust.
 
 ## Features
 
 - Thai word tokenizer
-  - use maximal-matching dictionary-based tokenization algorithm and honor Thai Character Cluster boundaries
-  - fast backend in Rust
-  - support custom dictionary
+  - Use maximal-matching dictionary-based tokenization algorithm
+    and honor [Thai Character Cluster][tcc] boundaries
+  - Fast backend in Rust
+  - Support custom dictionary
+
+[tcc]: https://dl.acm.org/doi/10.1145/355214.355225
 
 ## Build
 
@@ -26,14 +34,16 @@ npm run release
 ```
 
 Before build, your `nlpo3/` directory should look like this:
-```
+
+```text
 - nlpo3/
     - index.ts
     - rust_mod.d.ts
 ```
 
 After build:
-```
+
+```text
 - nlpo3/
     - index.js
     - index.ts
@@ -47,15 +57,16 @@ For now, copy the whole `nlpo3/` directory after build to your project.
 
 ### npm (experitmental)
 
-npm is still experimental and may not work on all platforms. Please report issues at https://github.com/PyThaiNLP/nlpo3/issues
+npm is still experimental and may not work on all platforms. Please report issues at <https://github.com/PyThaiNLP/nlpo3/issues>
 
-```bash
+```shell
 npm i nlpo3
 ```
 
 ## Usage
 
 In JavaScript:
+
 ```javascript
 const nlpO3 = require(`${path_to_nlpo3}`)
 
@@ -65,6 +76,7 @@ nloO3.segment("สวัสดีครับ", "dict_name")
 ```
 
 In TypeScript:
+
 ```typescript
 import {segment, loadDict} from `${path_to_nlpo3}/index`
 
@@ -75,8 +87,8 @@ segment("สวัสดีครับ", "dict_name")
 
 ## Issues
 
-Please report issues at https://github.com/PyThaiNLP/nlpo3/issues
+Please report issues at <https://github.com/PyThaiNLP/nlpo3/issues>
 
-# TODO
+## TODO
 
 - Find a way to build binaries and publish on npm.
diff --git a/nlpo3-nodejs/nlpo3/index.ts b/nlpo3-nodejs/nlpo3/index.ts
@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+// SPDX-License-Identifier: Apache-2.0
+
 import * as nativeModule from './rust_mod'
 /**
  * Load dict from dictionary file and store in hash map with key = dictName for ***segment*** function to use.

diff --git a/nlpo3-nodejs/nlpo3/rust_mod.d.ts b/nlpo3-nodejs/nlpo3/rust_mod.d.ts
@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+// SPDX-License-Identifier: Apache-2.0
+
 export function segment(text: string, dict_name: string, safe: boolean, parallel: boolean): string[];
 /** file_path is an absolute path */
 export function loadDict(file_path: string, dict_name: string): string;
diff --git a/nlpo3-nodejs/package.json b/nlpo3-nodejs/package.json
@@ -45,4 +45,4 @@
   "files": [
     "nlpo3"
   ]
-}
+}
diff --git a/nlpo3-nodejs/src/lib.rs b/nlpo3-nodejs/src/lib.rs
@@ -1,3 +1,6 @@
+// SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+// SPDX-License-Identifier: Apache-2.0
+
 use std::sync::Mutex;
 
 use ahash::AHashMap as HashMap;
@@ -6,7 +9,8 @@ use neon::prelude::*;
 use nlpo3::tokenizer::{newmm::NewmmTokenizer, tokenizer_trait::Tokenizer};
 
 lazy_static! {
-    static ref  DICT_COLLECTION:Mutex<HashMap<String,Box<NewmmTokenizer>>> = Mutex::new(HashMap::new());
+    static ref DICT_COLLECTION: Mutex<HashMap<String, Box<NewmmTokenizer>>> =
+        Mutex::new(HashMap::new());
 }
 
 fn load_dict(mut cx: FunctionContext) -> JsResult<JsString> {

diff --git a/nlpo3-python/Cargo.toml b/nlpo3-python/Cargo.toml
@@ -1,22 +1,23 @@
 [package]
 name = "nlpo3-python"
-version = "1.3.0"
+version = "1.3.1-dev"
 edition = "2018"
 license = "Apache-2.0"
 authors = ["Thanathip Suntorntip Gorlph"]
 description = "Python binding for nlpO3 Thai language processing library"
 exclude = ["notebooks"]
+keywords = ["thai", "tokenizer", "nlp", "word-segmentation", "python"]
 
 [lib]
 name = "_nlpo3_python_backend"
 path = "src/lib.rs"
 crate-type = ["cdylib", "rlib"]
 
 [dependencies]
-ahash = "0.7.6"
-lazy_static = "1.4.0"
-nlpo3 = "1.3.2"
+ahash = "0.8.6"
+lazy_static = "1.5.0"
+nlpo3 = "1.4.0"
 
 [dependencies.pyo3]
-version = "0.15.0"
+version = "0.22.6"
 features = ["extension-module"]
diff --git a/nlpo3-python/README.md b/nlpo3-python/README.md
@@ -1,28 +1,46 @@
-<a href="https://pypi.python.org/pypi/nlpo3"><img alt="pypi" src="https://img.shields.io/pypi/v/nlpo3.svg"/></a>
-<a href="https://www.python.org/downloads/release/python-360/"><img alt="Python 3.6" src="https://img.shields.io/badge/python-3.6-blue.svg"/></a>
-<a href="https://opensource.org/licenses/Apache-2.0"><img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"/></a>
-<a href="https://pepy.tech/project/nlpo3"><img alt="Downloads" src="https://pepy.tech/badge/nlpo3/month"/></a>
+---
+SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+SPDX-License-Identifier: Apache-2.0
+---
 
 # nlpO3 Python binding
 
+[![PyPI](https://img.shields.io/pypi/v/nlpo3.svg "PyPI")](https://pypi.python.org/pypi/nlpo3)
+[![Python 3.6](https://img.shields.io/badge/python-3.6-blue.svg "Python 3.6")](https://www.python.org/downloads/)
+[![Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg "Apache-2.0")](https://opensource.org/license/apache-2-0)
+
 Python binding for nlpO3, a Thai natural language processing library in Rust.
 
 ## Features
 
 - Thai word tokenizer
-  - `segment()` - use maximal-matching dictionary-based tokenization algorithm and honor Thai Character Cluster boundaries
-    - [2.5x faster](notebooks/nlpo3_segment_benchmarks.ipynb) than similar pure Python implementation (PyThaiNLP's newmm)
-  - `load_dict()` - load a dictionary from plain text file (one word per line)
+  - `segment()` - use maximal-matching dictionary-based tokenization algorithm
+    and honor [Thai Character Cluster][tcc] boundaries
+    - [2.5x faster][benchmark]
+      than similar pure Python implementation (PyThaiNLP's newmm)
+  - `load_dict()` - load a dictionary from a plain text file
+    (one word per line)
 
+[tcc]: https://dl.acm.org/doi/10.1145/355214.355225
+[benchmark]: ./notebooks/nlpo3_segment_benchmarks.ipynb
 
 ## Dictionary file
 
-- For the interest of library size, nlpO3 does not assume what dictionary the developer would like to use.
-  It does not come with a dictionary. A dictionary is needed for the dictionary-based word tokenizer.
+- For the interest of library size, nlpO3 does not assume what dictionary the
+  user would like to use, and it does not come with a dictionary.
+- A dictionary is needed for the dictionary-based word tokenizer.
 - For tokenization dictionary, try
-  - [words_th.tx](https://github.com/PyThaiNLP/pythainlp/blob/dev/pythainlp/corpus/words_th.txt) from [PyThaiNLP](https://github.com/PyThaiNLP/pythainlp/) - around 62,000 words (CC0)
-  - [word break dictionary](https://github.com/tlwg/libthai/tree/master/data) from [libthai](https://github.com/tlwg/libthai/) - consists of dictionaries in different categories, with make script (LGPL-2.1)
-
+  - [words_th.tx][dict-pythainlp] from [PyThaiNLP][pythainlp]
+    - ~62,000 words
+    - CC0-1.0
+  - [word break dictionary][dict-libthai] from [libthai][libthai]
+    - consists of dictionaries in different categories, with a make script
+    - LGPL-2.1
+
+[pythainlp]: https://github.com/PyThaiNLP/pythainlp
+[libthai]: https://github.com/tlwg/libthai/
+[dict-pythainlp]: https://github.com/PyThaiNLP/pythainlp/blob/dev/pythainlp/corpus/words_th.txt
+[dict-libthai]: https://github.com/tlwg/libthai/tree/master/data
 
 ## Install
 
@@ -34,6 +52,7 @@ pip install nlpo3
 
 Load file `path/to/dict.file` to memory and assign a name `dict_name` to it.
 Then tokenize a text with the `dict_name` dictionary:
+
 ```python
 from nlpo3 import load_dict, segment
 
@@ -42,18 +61,22 @@ segment("สวัสดีครับ", "dict_name")
 ```
 
 it will return a list of strings:
+
 ```python
 ['สวัสดี', 'ครับ']
 ```
+
 (result depends on words included in the dictionary)
 
 Use multithread mode, also use the `dict_name` dictionary:
+
 ```python
 segment("สวัสดีครับ", dict_name="dict_name", parallel=True)
 ```
 
 Use safe mode to avoid long waiting time in some edge cases
 for text with lots of ambiguous word boundaries:
+
 ```python
 segment("สวัสดีครับ", dict_name="dict_name", safe=True)
 ```
@@ -77,8 +100,9 @@ python -m pip install --upgrade build
 python -m build
 ```
 
-This should generate a wheel file, in `dist/` directory, which can be installed by pip.
+This should generate a wheel file, in `dist/` directory,
+which can be installed by pip.
 
 ## Issues
 
-Please report issues at https://github.com/PyThaiNLP/nlpo3/issues
+Please report issues at <https://github.com/PyThaiNLP/nlpo3/issues>
diff --git a/nlpo3-python/nlpo3/__init__.py b/nlpo3-python/nlpo3/__init__.py
@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2024 PyThaiNLP Project
+# SPDX-License-Identifier: Apache-2.0
+
 # Python-binding for nlpO3, an natural language process library.
 #
 # Provides a tokenizer.

diff --git a/nlpo3-python/pyproject.toml b/nlpo3-python/pyproject.toml
@@ -4,11 +4,11 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nlpo3"
-version = "1.3.0"
+version = "1.3.1-dev"
 description = "Python binding for nlpO3 Thai language processing library in Rust"
 readme = "README.md"
 requires-python = ">=3.6"
-license = {text = "Apache-2.0"}
+license = { text = "Apache-2.0" }
 keywords = ["thai", "tokenizer", "nlp", "word-segmentation", "pythainlp"]
 authors = [
   { name = "Thanathip Suntorntip" },
@@ -22,6 +22,10 @@ classifiers = [
   "Programming Language :: Python :: 3.7",
   "Programming Language :: Python :: 3.8",
   "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
   "Intended Audience :: Developers",
   "License :: OSI Approved :: Apache Software License",
   "Natural Language :: Thai",
@@ -43,7 +47,16 @@ wheel = "*"
 
 [tool.black]
 line-length = 79
-target_version = ['py36', 'py37', 'py38', 'py39']
+target_version = [
+  'py36',
+  'py37',
+  'py38',
+  'py39',
+  'py310',
+  'py311',
+  'py312',
+  'py313',
+]
 experimental_string_processing = true
 exclude = '''
 /(
-Original file line number
+Diff line change
@@ Expand Up / @@ -45,4 +45,4 @@ @@
       "files": [
         "nlpo3"
       ]
-    }
+    }