Merge pull request #317 from fergiemcdowall/316-enable-tree-shaking

316 enable tree shaking

.prettierrc.json

@@ -0,0 +1,7 @@
+{
+  "arrowParens": "avoid",
+  "bracketSpacing": true,
+  "semi": false,
+  "singleQuote": true,
+  "trailingComma": "none"
+}

dist/stopword.cjs.js

@@ -5148,7 +5148,7 @@ const hun = [
   'alóluk',
   'alólunk',
   'amely',
-  'amelybol',
+  'amelyből',
   'amelyek',
   'amelyekben',
   'amelyeket',
@@ -14273,16 +14273,12 @@ const zul = [
   'ngelinye'
 ];
 
-const defaultStopwords = eng;
-
-const removeStopwords = function (tokens, stopwords) {
-  stopwords = stopwords || defaultStopwords;
-  if (typeof tokens !== 'object' || typeof stopwords !== 'object') {
+// default to english stopword list
+const removeStopwords = (tokens, stopwords = eng) => {
+  if (!Array.isArray(tokens) || !Array.isArray(stopwords)) {
     throw new Error('expected Arrays try: removeStopwords(Array[, Array])')
   }
-  return tokens.filter(function (value) {
-    return stopwords.indexOf(value.toLowerCase()) === -1
-  })
+  return tokens.filter(x => !stopwords.includes(x.toLowerCase()))
 };
 
 exports._123 = _123;

dist/stopword.esm.mjs

@@ -5144,7 +5144,7 @@ const hun = [
   'alóluk',
   'alólunk',
   'amely',
-  'amelybol',
+  'amelyből',
   'amelyek',
   'amelyekben',
   'amelyeket',
@@ -14269,16 +14269,12 @@ const zul = [
   'ngelinye'
 ];
 
-const defaultStopwords = eng;
-
-const removeStopwords = function (tokens, stopwords) {
-  stopwords = stopwords || defaultStopwords;
-  if (typeof tokens !== 'object' || typeof stopwords !== 'object') {
+// default to english stopword list
+const removeStopwords = (tokens, stopwords = eng) => {
+  if (!Array.isArray(tokens) || !Array.isArray(stopwords)) {
     throw new Error('expected Arrays try: removeStopwords(Array[, Array])')
   }
-  return tokens.filter(function (value) {
-    return stopwords.indexOf(value.toLowerCase()) === -1
-  })
+  return tokens.filter(x => !stopwords.includes(x.toLowerCase()))
 };
 
 export { _123, afr, ara, ben, bre, bul, cat, ces, dan, deu, ell, eng, epo, est, eus, fas, fin, fra, gle, glg, guj, hau, heb, hin, hrv, hun, hye, ind, ita, jpn, kor, kur, lat, lav, lgg, lggNd, lit, mar, msa, mya, nld, nob, panGu, pol, por, porBr, removeStopwords, ron, rus, slk, slv, som, sot, spa, swa, swe, tgl, tha, tur, ukr, urd, vie, yor, zho, zul };

dist/stopword.umd.js

@@ -5150,7 +5150,7 @@
     'alóluk',
     'alólunk',
     'amely',
-    'amelybol',
+    'amelyből',
     'amelyek',
     'amelyekben',
     'amelyeket',
@@ -14275,16 +14275,12 @@
     'ngelinye'
   ];
 
-  const defaultStopwords = eng;
-
-  const removeStopwords = function (tokens, stopwords) {
-    stopwords = stopwords || defaultStopwords;
-    if (typeof tokens !== 'object' || typeof stopwords !== 'object') {
+  // default to english stopword list
+  const removeStopwords = (tokens, stopwords = eng) => {
+    if (!Array.isArray(tokens) || !Array.isArray(stopwords)) {
       throw new Error('expected Arrays try: removeStopwords(Array[, Array])')
     }
-    return tokens.filter(function (value) {
-      return stopwords.indexOf(value.toLowerCase()) === -1
-    })
+    return tokens.filter(x => !stopwords.includes(x.toLowerCase()))
   };
 
   exports._123 = _123;

package.json

@@ -1,18 +1,20 @@
 {
   "name": "stopword",
-  "version": "2.0.9",
+  "version": "3.0.0-rc3",
   "description": "A module for node.js and the browser that takes in text and returns text that is stripped of stopwords. Has pre-defined stopword lists for 62 languages and also takes lists with custom stopwords as input.",
-  "main": "./dist/stopword.cjs.js",
-  "module": "./dist/stopword.esm.mjs",
-  "browser": "./dist/stopword.umd.js",
+  "main": "./src/stopword.js",
+  "module": "./src/stopword.js",
+  "browser": "./src/stopword.js",
+  "jsdelivr": "./dist/stopword.umd.min.js",
   "files": [
     "./dist",
     "./src",
     "./rollup.config.js"
   ],
   "scripts": {
     "build": "rollup --config",
-    "test": "standard './*.js' './test/*.js' && npm run build && npx ava ./test/test.cjs.js && npx ava ./test/test.esm.mjs && npx ava ./test/ui-test.js"
+    "lint": "standard --fix ./*.js src/*.js test/*.js",
+    "test": "npm run lint && npm run build && npx ava ./test/test.cjs.js && npx ava ./test/test.esm.mjs && npx ava ./test/ui-test.js"
   },
   "repository": {
     "type": "git",
@@ -28,6 +30,7 @@
   ],
   "devDependencies": {
     "batr": "^2.1.10",
+    "standard": "^17.1.0",
     "words-n-numbers": "^9.1.2"
   },
   "author": "Fergus McDowall",

src/stopword.js

@@ -63,16 +63,78 @@ import { vie } from './stopwords_vie.js'
 import { yor } from './stopwords_yor.js'
 import { zul } from './stopwords_zul.js'
 
-const defaultStopwords = eng
-
-const removeStopwords = function (tokens, stopwords) {
-  stopwords = stopwords || defaultStopwords
-  if (typeof tokens !== 'object' || typeof stopwords !== 'object') {
+// default to english stopword list
+const removeStopwords = (tokens, stopwords = eng) => {
+  if (!Array.isArray(tokens) || !Array.isArray(stopwords)) {
     throw new Error('expected Arrays try: removeStopwords(Array[, Array])')
   }
-  return tokens.filter(function (value) {
-    return stopwords.indexOf(value.toLowerCase()) === -1
-  })
+  return tokens.filter(x => !stopwords.includes(x.toLowerCase()))
 }
 
-export { removeStopwords, _123, afr, ara, hye, eus, ben, bre, bul, cat, zho, hrv, ces, dan, nld, eng, epo, est, fin, fra, glg, deu, ell, guj, hau, heb, hin, hun, ind, gle, ita, jpn, kor, kur, lat, lav, lit, lgg, lggNd, msa, mar, mya, nob, fas, pol, por, porBr, panGu, ron, rus, slk, slv, som, sot, spa, swa, swe, tha, tgl, tur, urd, ukr, vie, yor, zul }
+export {
+  removeStopwords,
+  _123,
+  afr,
+  ara,
+  ben,
+  bre,
+  bul,
+  cat,
+  ces,
+  dan,
+  deu,
+  ell,
+  eng,
+  epo,
+  est,
+  eus,
+  fas,
+  fin,
+  fra,
+  gle,
+  glg,
+  guj,
+  hau,
+  heb,
+  hin,
+  hrv,
+  hun,
+  hye,
+  ind,
+  ita,
+  jpn,
+  kor,
+  kur,
+  lat,
+  lav,
+  lgg,
+  lggNd,
+  lit,
+  mar,
+  msa,
+  mya,
+  nld,
+  nob,
+  panGu,
+  pol,
+  por,
+  porBr,
+  ron,
+  rus,
+  slk,
+  slv,
+  som,
+  sot,
+  spa,
+  swa,
+  swe,
+  tgl,
+  tha,
+  tur,
+  ukr,
+  urd,
+  vie,
+  yor,
+  zho,
+  zul
+}

src/stopwords__123.js

@@ -1,4 +1,3 @@
-
 const num123 = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9']
 const numFas = ['۱', '۲', '۳', '۴', '۵', '۶', '۷', '۸', '۹', '۰']
 const numKor = ['０', '１', '２', '３', '４', '５', '６', '７', '８', '９']