Merge pull request #49 from bact/main

Update doc for Python binding

Cargo.toml

@@ -38,8 +38,8 @@ anyhow = "1.0.45"
 binary-heap-plus = "0.4.1"
 bytecount = "0.6.2"
 lazy_static = "1.4.0"
-rayon = "1.5"
-regex = "1.4.6"
+rayon = "1.5.1"
+regex = "1.5.4"
 rustc-hash = "1.1.0"
 
 

nlpo3-nodejs/Cargo.toml

@@ -10,7 +10,7 @@ exclude = ["index.node"]
 crate-type = ["cdylib"]
 
 [dependencies]
-ahash = "0.7.2"
+ahash = "0.7.6"
 lazy_static = "1.4.0"
 nlpo3 = "1.2.0"
 

nlpo3-python/Cargo.toml

@@ -13,7 +13,7 @@ path = "src/lib.rs"
 crate-type = ["cdylib", "rlib"]
 
 [dependencies]
-ahash = "0.7.2"
+ahash = "0.7.6"
 lazy_static = "1.4.0"
 nlpo3 = "1.3.1"
 

nlpo3-python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nlpo3"
-version = "1.1.3"
+version = "1.2.0"
 description = "Python binding for nlpO3 Thai language processing library in Rust"
 readme = "README.md"
 requires-python = ">=3.6"

nlpo3-python/setup.cfg

@@ -1,43 +1,40 @@
 [metadata]
 name = nlpo3
-version = 1.1.3
+version = 1.2.0
 description = Python binding for nlpO3 Thai language processing library
 long_description =
  Python 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
+ - use user-supplied dictionary
  - 2.5x faster than similar pure Python implementation
- - built-in dictionary included (62,000 words, a copy from PyThaiNLP)
- - support custom dictionary
-
-
+
  ## Install
- 
+
  ```bash
  pip install nlpo3
  ```
- 
+
  ## Usage
-
- Tokenization using default dictionary:
- ```python
- from nlpo3 import segment
-
- segment("สวัสดีครับ") # returns ["สวัสดี", "ครับ"]
- ```
 
  Load file `path/to/dict.file` to memory and assigned it with name `custom_dict`.
  Then tokenize a text with `custom_dict` dictionary:
  ```python
  from nlpo3 import load_dict, segment
- 
+
  load_dict("path/to/dict.file", "custom_dict")
  segment("สวัสดีครับ", "custom_dict")
  ```
-
+
+ it will return a list of strings:
+ ```python
+ ['สวัสดี', 'ครับ']
+ ```
+ (result depends on words included in the dictionary)
+
  For more documentation, go [https://github.com/PyThaiNLP/nlpo3](https://github.com/PyThaiNLP/nlpo3)
 
 long_description_content_type = text/markdown