Merge pull request #274 from fergiemcdowall/v2

V2 - import destructuring, ISO 639-3 language codes + 5 more languages + lots more

.github/workflows/tests.yml

@@ -0,0 +1,18 @@
+name: tests
+on:
+  - push
+  - pull_request
+jobs:
+  run-tests:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        node-version: [12.x, 14.x, 16.x]
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/setup-node@v2
+        with:
+          node-version: ${{ matrix.node-version }}
+      - run: npm install
+      - run: sudo apt-get install xvfb
+      - run: xvfb-run --auto-servernum npm test

LICENSE

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2015 Fergus McDowall
+Copyright (c) 2015 - 2022 Fergus McDowall
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -19,4 +19,3 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
-

README.md

@@ -1,75 +1,113 @@
 # stopword
 `stopword` is a module for node and the browser that allows you to strip
-stopwords from an input text. [In natural language processing, "Stopwords" are
+stopwords from an input text. Covers 62 languages. [In natural language processing, "Stopwords" are
 words that are so frequent that they can safely be removed from a text without
 altering its meaning.](https://en.wikipedia.org/wiki/Stop_words)
 
+## Breaking change!
+Language codes are changed from ISO-639-1 (two characters) to ISO-639-3. This to have room for more small languages that wasn't specified in ISO-639-1.
+
 [![NPM version][npm-version-image]][npm-url]
 [![NPM downloads][npm-downloads-image]][npm-url]
-[![Build Status][travis-image]][travis-url]
+[![Build Status][CI-image]][CI-url]
 [![JavaScript Style Guide][standardjs-image]][standardjs-url]
 [![MIT License][license-image]][license-url]
 
 ![wonderful day stopword module](./demo/stopword-demo.gif)
 
 Live [stopword browser demo](http://fergiemcdowall.github.io/stopword/demo/).
 
-## Usage
+## Getting the script in your environment
+
+### CJS - CommonJS
+Deconstruction require:
+```javascript
+const { removeStopwords, eng, fra } = require('stopword')
+// 'removeStopwords', 'eng' and 'fra' available
+```
+
+Old style require:
+```javascript
+const sw = require('stopword')
+// sw.removeStopwords and sw.<language codes> now available
+```
+
+### ESM - Ecmascript Modules
+Deconstruction import:
+```javascript
+import { removeStopwords, eng, fra } from './dist/stopword.esm.mjs'
+// 'removeStopwords', 'eng' and 'fra' available
+```
 
-### Node.js
+Old style import:
 ```javascript
-sw = require('stopword')
-// sw.removeStopwords and sw.[language code] now available
+import * as sw from './dist/stopword.esm.mjs'
+// 'sw.removeStopwords' + 'sw.<language codes>' available
 ```
 
-### Script tag method
+### UMD - Script tag method
 ```html
-<script src="stopword.js"></script>
+<script src="stopword.umd.js"></script>
 
 <script>
-// sw.removeStopwords and sw.[language code] now available
+// sw.removeStopwords and sw.<language codes> now available
 </script>
 ```
 
 
+## Usage
+
 ### Default (English)
 By default, `stopword` will strip an array of "meaningless" English words
 
-```javascript
-sw = require('stopword')
+```javaScript
+const { removeStopwords } = require('stopword')
 const oldString = 'a really Interesting string with some words'.split(' ')
-const newString = sw.removeStopwords(oldString)
+const newString = removeStopwords(oldString)
 // newString is now [ 'really', 'Interesting', 'string', 'words' ]
 
 ```
 
 ### Other languages
 You can also specify a language other than English:
-```javascript
-sw = require('stopword')
+```javaScript
+const { removeStopwords, swe } = require('stopword')
 const oldString = 'Trädgårdsägare är beredda att pröva vad som helst för att bli av med de hatade mördarsniglarna åäö'.split(' ')
-// sw.sv contains swedish stopwords
-const newString = sw.removeStopwords(oldString, sw.sv)
+// swe contains swedish stopwords
+const newString = removeStopwords(oldString, swe)
 // newString is now [ 'Trädgårdsägare', 'beredda', 'pröva', 'helst', 'hatade', 'mördarsniglarna', 'åäö' ]
 ```
 
+### Numbers
+Extract numbers (korean script/characters) with module `words-n-numbers` and removing 0-9 'stopwords'
+
+```javaScript
+const { removeStopwords, swe } = require('stopword')
+const { extract, words, numbers } = require('words-n-numbers')
+const oldString = '쾰른 대성당(독일어: Kölner Dom, 정식 명칭: Hohe Domkirche St. Peter)은 독일 쾰른에 있는 로마 가톨릭교회의 성당이다. 고딕 양식으로 지어졌다. 쾰른 대교구의 주교좌 성당이라 쾰른 주교좌 성당이라고도 불린다. 현재 쾰른 대교구의 교구장은 라이너 마리아 뵐키 추기경이다. 이 성당은 독일에서 가장 잘 알려진 건축물로, 성 바실리 대성당에 이어, 1996년 유네스코 세계유산으로 등재되었다. 유네스코에서는 쾰른 대성당을 일컬어 “인류의 창조적 재능을 보여주는 드문 작품”이라고 묘사하였다.[1] 매일 2만여 명의 관광객이 이 성당을 찾는다.[2]'
+let newString = extract(oldString, { regex: [numbers] })
+newString = removeStopwords(newString, _123)
+// newString is now [ '1996' ]
+})
+```
+
 ### Custom list of stopwords
 And last, but not least, it is possible to use your own, custom list of stopwords:
 ```javascript
-sw = require('stopword')
+const { removeStopwords } = require('stopword')
 const oldString = 'you can even roll your own custom stopword list'.split(' ')
 // Just add your own list/array of stopwords
-const newString = sw.removeStopwords(oldString, [ 'even', 'a', 'custom', 'stopword', 'list', 'is', 'possible']
+const newString = removeStopwords(oldString, [ 'even', 'a', 'custom', 'stopword', 'list', 'is', 'possible']
 // newString is now [ 'you', 'can', 'roll', 'your', 'own']
 ```
 
 ### Removing stopwords for i.e. two languages and a custom stopword list
 With spread syntax you can easily combine several stopword arrays into one. Useful for situations where two langauages are used interchangeably. Or when you have certain words that are used in every document that is not in your existing stopword arrays.
 ```javascript
-sw = require('stopword')
+const { removeStopwords, eng, swe } = require('stopword')
 const oldString = 'a really interesting string with some words trädgårdsägare är beredda att pröva vad som helst för att bli av med de hatade mördarsniglarna'.split(' ')
 const customStopwords = ['interesting', 'really']
-const newString = sw.removeStopwords(oldString, [...sw.en, ...sw.sv, ...customStopwords]
+const newString = sw.removeStopwords(oldString, [...eng, ...swe, ...customStopwords]
 // newString is now ['string', 'words', 'trädgårdsägare', 'beredda', 'pröva', 'helst', 'hatade', 'mördarsniglarna']
 ```
 
@@ -85,95 +123,103 @@ Returns an Array that represents the text with the specified stopwords removed.
 * `stopwords` An array of stopwords
 
 ```javascript
-sw = require('stopword')
-var text = sw.removeStopwords(text[, stopwords])
+const { removeStopwords } = require('stopword')
+var text = removeStopwords(text[, stopwords])
 // text is now an array of given words minus specified stopwords
 ```
 
 ### &lt;language code&gt;
 
-Arrays of stopwords for the following 57 languages are supplied: 
-
-* `af` - Afrikaans
-* `ar` - Arabic, Modern Standard
-* `hy` - Armenian
-* `eu` - Basque
-* `bn` - Bengali
-* `br` - Breton
-* `bg` - Bulgarian
-* `ca` - Catalan
-* `zh` - Chinese Simplified
-* `hr` - Croatian
-* `cs` - Czech
-* `da` - Danish
-* `nl` - Dutch
-* `en` - English
-* `eo` - Esperanto
-* `et` - Estonian
-* `fa` - Farsi
-* `fi` - Finnish
-* `fr` - French
-* `gl` - Galician
-* `de` - German
-* `el` - Greek
-* `ha` - Hausa
-* `he` - Hebrew
-* `hi` - Hindi
-* `hu` - Hungarian
-* `id` - Indonesian
-* `ga` - Irish
-* `it` - Italian
-* `ja` - Japanese
-* `ko` - Korean
-* `la` - Latin
-* `lv` - Latvian
-* `lgg` - Lugbara (without diacritics)
-* `lggo` - Lugbara official (with diacritics)
-* `mr` - Marathi
-* `my` - Myanmar
-* `no` - Norwegian
-* `pl` - Polish
-* `pt` - Portuguese
-* `ptbr` - Portuguese (Brazilian)
-* `pa` - Punjabi Gurmukhi
-* `ro` - Romanian
-* `ru` - Russian
-* `sk` - Slovak
-* `sl` - Slovenian
-* `so` - Somali
-* `st` - Sotho
-* `es` - Spanish
-* `sw` - Swahili
-* `sv` - Swedish
-* `th` - Thai
-* `tl` - Tagalog (Filipino)
-* `tr` - Turkish
-* `ur` - Urdu
-* `vi` - Vietnamese
-* `yo` - Yoruba
-* `zu` - Zulu
+Language codes follow [ISO 639-3 Language Code list](https://iso639-3.sil.org/code_tables/639/data/all). Arrays of stopwords for the following 62 languages are supplied:
+
+* `_123` - 0-9 for different script (regular, Farsi, Korean and Myanmar)
+* `afr` - Afrikaans
+* `ara` - Arabic, Macrolanguage
+* `hye` - Armenian
+* `eus` - Basque
+* `ben` - Bengali
+* `bre` - Breton
+* `bul` - Bulgarian
+* `cat` - Catalan, Valencian 
+* `zho` - Chinese, Macrolanguage
+* `hrv` - Croatian
+* `ces` - Czech
+* `dan` - Danish
+* `nld` - Dutch
+* `eng` - English
+* `epo` - Esperanto
+* `est` - Estonian, Macrolanguage
+* `fin` - Finnish
+* `fra` - French
+* `glg` - Galician
+* `deu` - German
+* `ell` - Greek, Modern
+* `guj` - Gujarati
+* `hau` - Hausa
+* `heb` - Hebrew
+* `hin` - Hindi
+* `hun` - Hungarian
+* `ind` - Indonesian
+* `gle` - Irish
+* `ita` - Italian
+* `jpn` - Japanese
+* `kor` - Korean
+* `kur` - Kurdish, Macrolanguage
+* `lat` - Latin
+* `lav` - Latvian, Macrolanguage
+* `lit` - Lithuanian
+* `lgg` - Lugbara
+* `lggNd` - Lugbara, No diacritics
+* `msa` - Malay, Macrolanguage
+* `mar` - Marathi
+* `mya` - Myanmar (Burmese)
+* `nob` - Norwegian bokmål
+* `fas` - Persian (Farsi)
+* `pol` - Polish
+* `por` - Portuguese
+* `porBr` - Portuguese-Brazilian
+* `panGu` - Punjabi (Panjabi), Gurmukhi script
+* `ron` - Romanian (Moldavian, Moldovan)
+* `rus` - Russian
+* `slk` - Slovak
+* `slv` - Slovenian
+* `som` - Somali
+* `sot` - Sotho, Southern
+* `spa` - Spanish
+* `swa` - Swahili, Macrolanguage
+* `swe` - Swedish
+* `tha` - Thai
+* `tgl` - Tagalog (Filipino)
+* `tur` - Turkish
+* `ukr` - Ukrainian
+* `urd` - Urdu
+* `vie` - Vietnamese
+* `yor` - Yoruba
+* `zul` - Zulu
 
 ```javascript
-sw = require('stopword')
-norwegianStopwords = sw.no
-// norwegianStopwords now contains an Array of norwgian stopwords
+const { nob } = require('stopword')
+norwegianBokmaalStopwords = nob
+// norwegianBokmaalStopwords now contains an Array of norwgian bokmål stopwords
 ```
 
 #### Languages with no space between words
-`ja` Japanese, `th` Thai and `zh` Chinese Simplified and some of the other languages supported have no space between words. For these languages you need to split the text into an array of words in another way than just `textString.split(' ')`. You can check out [TinySegmenter](http://chasen.org/%7Etaku/software/TinySegmenter/) for Japanese and [chinese-tokenizer](https://github.com/yishn/chinese-tokenizer) for Chinese.
+`jpn` Japanese, `tha` Thai and `zho` Chinese and some of the other languages supported have no space between words. For these languages you need to split the text into an array of words in another way than just `textString.split(' ')`. You can check out [TinySegmenter](http://chasen.org/%7Etaku/software/TinySegmenter/) for Japanese and [chinese-tokenizer](https://github.com/yishn/chinese-tokenizer) for Chinese.
 
 ## Your language missing?
 If you can't find a stopword file for your language, you can try creating one with [`stopword-trainer`](https://github.com/eklem/stopword-trainer). We're happy to help you in the process.
 
-## Contributions
+## Contributions and licenses
 Most of this work is from other projects and people, and wouldn't be possible without them. Thanks to among others the [stopwords-iso](https://github.com/stopwords-iso) project and the [more-stoplist](https://github.com/dohliam/more-stoplists) project. And thanks for all your code input: @arthurdenner, @micalevisk, @fabric-io-rodrigues, @behzadmoradi, @guysaar223, @ConnorKrammer, @GreXLin85, @nanopx, @virtual and @JustroX!
 
+[Licenses](./dist/LICENSES.txt) for this library and all third party code.
+
 [license-image]: http://img.shields.io/badge/license-MIT-blue.svg?style=flat
 [license-url]: LICENSE
 [npm-url]: https://npmjs.org/package/stopword
 [npm-version-image]: http://img.shields.io/npm/v/stopword.svg?style=flat
 [npm-downloads-image]: http://img.shields.io/npm/dm/stopword.svg?style=flat
-[travis-url]: http://travis-ci.org/fergiemcdowall/stopword
-[travis-image]: http://img.shields.io/travis/fergiemcdowall/stopword.svg?style=flat
+[CI-url]: https://github.com/fergiemcdowall/stopword/actions/workflows/tests.yml
+[CI-image]: https://github.com/fergiemcdowall/stopword/actions/workflows/tests.yml/badge.svg
 [standardjs-url]: https://standardjs.com
 [standardjs-image]: https://img.shields.io/badge/code_style-standard-brightgreen.svg?style=flat-square

demo/index.html

@@ -5,7 +5,7 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <link rel="stylesheet" href="./mini-default.min.css" />
     <link rel="stylesheet" href="./mini-additions.css" />
-    <script src="../dist/stopword.js"></script>
+    <script src="../dist/stopword.umd.js"></script>
     <title>Stopword browser demo</title>
   </head>
 

demo/stopword-app.js

@@ -2,7 +2,7 @@ const languageSelect = document.getElementById('languages')
 const sentenceInput = document.getElementById('text')
 const resultText = document.getElementById('stopwordsRemoved')
 
-function updateSentence() {
+function updateSentence () {
   const language = languageSelect.value
   const oldString = sentenceInput.value.split(' ')
   const newString = sw.removeStopwords(oldString, sw[language]).join(' ')