natural 0.5.4 → 0.6.1

package/lib/natural/tokenizers/aggressive_tokenizer_id.js

@@ -0,0 +1,44 @@
+/*
+Copyright (c) 2017, Alif Bhaskoro, Andy Librian, R. Kukuh (Reimplemented from https://github.com/sastrawi/sastrawi)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+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.
+*/
+
+var Tokenizer = require('./tokenizer'),
+    util = require('util');
+
+var AggressiveTokenizer = function() {
+    Tokenizer.call(this);    
+};
+util.inherits(AggressiveTokenizer, Tokenizer);
+
+module.exports = AggressiveTokenizer;
+
+// Remove all non alphanumeric characters except '-'
+// Replace more than one space character to ' '
+function normalizeText(text){
+	result = text.replace(/[^a-z0-9 -]/g, ' ').replace(/( +)/g, ' ');
+	return result;
+}
+
+AggressiveTokenizer.prototype.tokenize = function(text) {
+    // break a string up into an array of tokens by space
+    text = normalizeText(text);
+    return this.trim(text.split(' '));
+};

package/lib/natural/tokenizers/aggressive_tokenizer_sv.js

@@ -0,0 +1,40 @@
+/*
+Copyright (c) 2017, Dogan Yazar
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+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.
+*/
+
+var Tokenizer = require('./tokenizer'),
+    normalizer = require('../normalizers/normalizer_sv'),
+    util = require('util');
+
+var AggressiveTokenizer = function() {
+    Tokenizer.call(this);
+};
+util.inherits(AggressiveTokenizer, Tokenizer);
+
+module.exports = AggressiveTokenizer;
+
+AggressiveTokenizer.prototype.tokenize = function(text) {
+    text = normalizer.remove_diacritics(text);
+
+    // break a string up into an array of tokens by anything non-word
+    // Ü is not part of swedish alphabet but there are words using it like müsli and München 
+    return this.trim(text.split(/[^A-Za-z0-9_åÅäÄöÖüÜ]+/));
+};

package/lib/natural/tokenizers/aggressive_tokenizer_vi.js

@@ -0,0 +1,37 @@
+/*
+Copyright (c) 2018, Javis1205 (Github account name)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+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.
+*/
+
+var Tokenizer = require('./tokenizer'),
+util = require('util');
+
+var AggressiveTokenizer = function() {
+  Tokenizer.call(this);
+};
+
+util.inherits(AggressiveTokenizer, Tokenizer);
+
+// break a string up into an array of tokens by anything non-word
+AggressiveTokenizer.prototype.tokenize = function(text) {
+  return this.trim(text.split(/[^a-z0-9àáảãạăắằẳẵặâấầẩẫậéèẻẽẹêếềểễệíìỉĩịóòỏõọôốồổỗộơớờởỡợúùủũụưứừửữựýỳỷỹỵđ]+/i));
+};
+
+module.exports = AggressiveTokenizer;

package/lib/natural/tokenizers/orthography_matchers.js

@@ -0,0 +1,33 @@
+/*
+Copyright (c) 2011, Chris Umbel
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+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.
+*/
+
+
+/***
+ * RegExp definitions for tokenizing text in a specific language based
+ * on its alphabet. Each language is keyed by the two-letter code per
+ * ISO 639-1, and defines a RegExp that excludes alphabetic characters.
+ */
+var matchers = {
+  fi: /[^A-Za-zÅåÄäÖö]/
+};
+
+module.exports = matchers;

package/lib/natural/tokenizers/regexp_tokenizer.js

@@ -32,7 +32,7 @@ var RegexpTokenizer = function(options) {
 
     // Match and split on GAPS not the actual WORDS
     this._gaps = options.gaps;
-    
+
     if (this._gaps === undefined) {
         this._gaps = true;
     }
@@ -53,13 +53,33 @@ RegexpTokenizer.prototype.tokenize = function(s) {
 
 exports.RegexpTokenizer = RegexpTokenizer;
 
+var orthographyMatchers = require('./orthography_matchers');
+
+/***
+ * A tokenizer that accepts an alphabet definition.
+ * @param {string} options.language ISO 639-1 for the language, e.g. 'en'
+ */
+var OrthographyTokenizer = function(options) {
+    var pattern = orthographyMatchers[options.language];
+    if (!pattern) {
+        WordTokenizer.call(this, options);
+    } else {
+        this._pattern = pattern;
+        RegexpTokenizer.call(this, options);
+    }
+};
+
+util.inherits(OrthographyTokenizer, RegexpTokenizer);
+
+exports.OrthographyTokenizer = OrthographyTokenizer;
+
 /***
  * A tokenizer that divides a text into sequences of alphabetic and
  * non-alphabetic characters.  E.g.:
  *
  *      >>> WordTokenizer().tokenize("She said 'hello'.")
  *      ['She', 'said', 'hello']
- * 
+ *
  */
 var WordTokenizer = function(options) {
     this._pattern = /[^A-Za-zА-Яа-я0-9_]+/;
@@ -75,7 +95,7 @@ exports.WordTokenizer = WordTokenizer;
  *
  *      >>> WordPunctTokenizer().tokenize("She said 'hello'.")
  *      ["She","said","'","hello","'","."]
- * 
+ *
  */
 var WordPunctTokenizer = function(options) {
     this._pattern = new RegExp(/(\w+|[а-я0-9_]+|\.|\!|\'|\"")/i);

package/lib/natural/tokenizers/sentence_tokenizer.js

@@ -30,7 +30,7 @@ util.inherits(SentenceTokenizer, Tokenizer);
 
 SentenceTokenizer.prototype.tokenize = function(text) {
     // break string up in to sentences based on punctation and quotation marks
-    var tokens = text.match(/([\"\'\‘\“\'\"\[\(\{\⟨][^\.\?\!]+[\.\?\!][\"\'\’\”\'\"\]\)\}\⟩]|[^\.\?\!]+[\.\?\!])\s?/g);
+    var tokens = text.match(/([\"\'\‘\“\'\"\[\(\{\⟨][^\.\?\!]+[\.\?\!][\"\'\’\”\'\"\]\)\}\⟩]|[^\.\?\!]+[\.\?\!\s]+)\s?/g);
 
     // remove unecessary white space
     tokens = tokens.map(Function.prototype.call, String.prototype.trim);

package/lib/natural/util/stopwords_id.js

@@ -0,0 +1,119 @@
+/*
+Copyright (c) 2017, Alif Bhaskoro, Andy Librian, R. Kukuh (Reimplemented from https://github.com/sastrawi/sastrawi)
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+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.
+*/
+
+// a list of commonly used words that have little meaning and can be excluded
+// from analysis.
+var words = 
+	['a','ada','adalah','adanya','adapun','agak','agaknya','agar','akan','akankah','akhir',
+    'akhiri','akhirnya','aku','akulah','amat','amatlah','anda','andalah','antar','antara',
+    'antaranya','apa','apaan','apabila','apakah','apalagi','apatah','arti','artinya','asal',
+    'asalkan','atas','atau','ataukah','ataupun','awal','awalnya','b','bagai','bagaikan',
+    'bagaimana','bagaimanakah','bagaimanapun','bagainamakah','bagi','bagian','bahkan','bahwa',
+    'bahwasannya','bahwasanya','baik','baiklah','bakal','bakalan','balik','banyak','bapak',
+    'baru','bawah','beberapa','begini','beginian','beginikah','beginilah','begitu','begitukah',
+    'begitulah','begitupun','bekerja','belakang','belakangan','belum','belumlah','benar',
+    'benarkah','benarlah','berada','berakhir','berakhirlah','berakhirnya','berapa','berapakah',
+    'berapalah','berapapun','berarti','berawal','berbagai','berdatangan','beri','berikan',
+    'berikut','berikutnya','berjumlah','berkali-kali','berkata','berkehendak','berkeinginan',
+    'berkenaan','berlainan','berlalu','berlangsung','berlebihan','bermacam','bermacam-macam',
+    'bermaksud','bermula','bersama','bersama-sama','bersiap','bersiap-siap','bertanya',
+    'bertanya-tanya','berturut','berturut-turut','bertutur','berujar','berupa','besar',
+    'betul','betulkah','biasa','biasanya','bila','bilakah','bisa','bisakah','boleh','bolehkah',
+    'bolehlah','buat','bukan','bukankah','bukanlah','bukannya','bulan','bung','c','cara',
+    'caranya','cukup','cukupkah','cukuplah','cuma','d','dahulu','dalam','dan','dapat','dari',
+    'daripada','datang','dekat','demi','demikian','demikianlah','dengan','depan','di','dia',
+    'diakhiri','diakhirinya','dialah','diantara','diantaranya','diberi','diberikan','diberikannya',
+    'dibuat','dibuatnya','didapat','didatangkan','digunakan','diibaratkan','diibaratkannya',
+    'diingat','diingatkan','diinginkan','dijawab','dijelaskan','dijelaskannya','dikarenakan',
+    'dikatakan','dikatakannya','dikerjakan','diketahui','diketahuinya','dikira','dilakukan',
+    'dilalui','dilihat','dimaksud','dimaksudkan','dimaksudkannya','dimaksudnya','diminta',
+    'dimintai','dimisalkan','dimulai','dimulailah','dimulainya','dimungkinkan','dini','dipastikan',
+    'diperbuat','diperbuatnya','dipergunakan','diperkirakan','diperlihatkan','diperlukan',
+    'diperlukannya','dipersoalkan','dipertanyakan','dipunyai','diri','dirinya','disampaikan',
+    'disebut','disebutkan','disebutkannya','disini','disinilah','ditambahkan','ditandaskan',
+    'ditanya','ditanyai','ditanyakan','ditegaskan','ditujukan','ditunjuk','ditunjuki','ditunjukkan',
+    'ditunjukkannya','ditunjuknya','dituturkan','dituturkannya','diucapkan','diucapkannya',
+    'diungkapkan','dong','dua','dulu','e','empat','enak','enggak','enggaknya','entah','entahlah',
+    'f','g','guna','gunakan','h','hadap','hai','hal','halo','hallo','hampir','hanya','hanyalah',
+    'hari','harus','haruslah','harusnya','helo','hello','hendak','hendaklah','hendaknya','hingga',
+    'i','ia','ialah','ibarat','ibaratkan','ibaratnya','ibu','ikut','ingat','ingat-ingat','ingin',
+    'inginkah','inginkan','ini','inikah','inilah','itu','itukah','itulah','j','jadi','jadilah',
+    'jadinya','jangan','jangankan','janganlah','jauh','jawab','jawaban','jawabnya','jelas',
+    'jelaskan','jelaslah','jelasnya','jika','jikalau','juga','jumlah','jumlahnya','justru',
+    'k','kadar','kala','kalau','kalaulah','kalaupun','kali','kalian','kami','kamilah','kamu',
+    'kamulah','kan','kapan','kapankah','kapanpun','karena','karenanya','kasus','kata','katakan',
+    'katakanlah','katanya','ke','keadaan','kebetulan','kecil','kedua','keduanya','keinginan',
+    'kelamaan','kelihatan','kelihatannya','kelima','keluar','kembali','kemudian','kemungkinan',
+    'kemungkinannya','kena','kenapa','kepada','kepadanya','kerja','kesampaian','keseluruhan',
+    'keseluruhannya','keterlaluan','ketika','khusus','khususnya','kini','kinilah','kira',
+    'kira-kira','kiranya','kita','kitalah','kok','kurang','l','lagi','lagian','lah','lain',
+    'lainnya','laku','lalu','lama','lamanya','langsung','lanjut','lanjutnya','lebih','lewat',
+    'lihat','lima','luar','m','macam','maka','makanya','makin','maksud','malah','malahan',
+    'mampu','mampukah','mana','manakala','manalagi','masa','masalah','masalahnya','masih',
+    'masihkah','masing','masing-masing','masuk','mata','mau','maupun','melainkan','melakukan',
+    'melalui','melihat','melihatnya','memang','memastikan','memberi','memberikan','membuat',
+    'memerlukan','memihak','meminta','memintakan','memisalkan','memperbuat','mempergunakan',
+    'memperkirakan','memperlihatkan','mempersiapkan','mempersoalkan','mempertanyakan','mempunyai',
+    'memulai','memungkinkan','menaiki','menambahkan','menandaskan','menanti','menanti-nanti',
+    'menantikan','menanya','menanyai','menanyakan','mendapat','mendapatkan','mendatang','mendatangi',
+    'mendatangkan','menegaskan','mengakhiri','mengapa','mengatakan','mengatakannya','mengenai',
+    'mengerjakan','mengetahui','menggunakan','menghendaki','mengibaratkan','mengibaratkannya',
+    'mengingat','mengingatkan','menginginkan','mengira','mengucapkan','mengucapkannya','mengungkapkan',
+    'menjadi','menjawab','menjelaskan','menuju','menunjuk','menunjuki','menunjukkan','menunjuknya',
+    'menurut','menuturkan','menyampaikan','menyangkut','menyatakan','menyebutkan','menyeluruh',
+    'menyiapkan','merasa','mereka','merekalah','merupakan','meski','meskipun','meyakini','meyakinkan',
+    'minta','mirip','misal','misalkan','misalnya','mohon','mula','mulai','mulailah','mulanya','mungkin',
+    'mungkinkah','n','nah','naik','namun','nanti','nantinya','nya','nyaris','nyata','nyatanya',
+    'o','oleh','olehnya','orang','p','pada','padahal','padanya','pak','paling','panjang','pantas',
+    'para','pasti','pastilah','penting','pentingnya','per','percuma','perlu','perlukah','perlunya',
+    'pernah','persoalan','pertama','pertama-tama','pertanyaan','pertanyakan','pihak','pihaknya',
+    'pukul','pula','pun','punya','q','r','rasa','rasanya','rupa','rupanya','s','saat','saatnya','saja',
+    'sajalah','salam','saling','sama','sama-sama','sambil','sampai','sampai-sampai','sampaikan','sana',
+    'sangat','sangatlah','sangkut','satu','saya','sayalah','se','sebab','sebabnya','sebagai',
+    'sebagaimana','sebagainya','sebagian','sebaik','sebaik-baiknya','sebaiknya','sebaliknya',
+    'sebanyak','sebegini','sebegitu','sebelum','sebelumnya','sebenarnya','seberapa','sebesar',
+    'sebetulnya','sebisanya','sebuah','sebut','sebutlah','sebutnya','secara','secukupnya','sedang',
+    'sedangkan','sedemikian','sedikit','sedikitnya','seenaknya','segala','segalanya','segera',
+    'seharusnya','sehingga','seingat','sejak','sejauh','sejenak','sejumlah','sekadar','sekadarnya',
+    'sekali','sekali-kali','sekalian','sekaligus','sekalipun','sekarang','sekaranglah','sekecil',
+    'seketika','sekiranya','sekitar','sekitarnya','sekurang-kurangnya','sekurangnya','sela','selain',
+    'selaku','selalu','selama','selama-lamanya','selamanya','selanjutnya','seluruh','seluruhnya',
+    'semacam','semakin','semampu','semampunya','semasa','semasih','semata','semata-mata','semaunya',
+    'sementara','semisal','semisalnya','sempat','semua','semuanya','semula','sendiri','sendirian',
+    'sendirinya','seolah','seolah-olah','seorang','sepanjang','sepantasnya','sepantasnyalah',
+    'seperlunya','seperti','sepertinya','sepihak','sering','seringnya','serta','serupa','sesaat',
+    'sesama','sesampai','sesegera','sesekali','seseorang','sesuatu','sesuatunya','sesudah',
+    'sesudahnya','setelah','setempat','setengah','seterusnya','setiap','setiba','setibanya',
+    'setidak-tidaknya','setidaknya','setinggi','seusai','sewaktu','siap','siapa','siapakah',
+    'siapapun','sini','sinilah','soal','soalnya','suatu','sudah','sudahkah','sudahlah','supaya',
+    't','tadi','tadinya','tahu','tak','tambah','tambahnya','tampak','tampaknya','tandas','tandasnya',
+    'tanpa','tanya','tanyakan','tanyanya','tapi','tegas','tegasnya','telah','tempat','tentang','tentu',
+    'tentulah','tentunya','tepat','terakhir','terasa','terbanyak','terdahulu','terdapat','terdiri',
+    'terhadap','terhadapnya','teringat','teringat-ingat','terjadi','terjadilah','terjadinya','terkira',
+    'terlalu','terlebih','terlihat','termasuk','ternyata','tersampaikan','tersebut','tersebutlah',
+    'tertentu','tertuju','terus','terutama','tetap','tetapi','tiap','tiba','tiba-tiba','tidak',
+    'tidakkah','tidaklah','tiga','toh','tuju','tunjuk','turut','tutur','tuturnya','u','ucap','ucapnya',
+    'ujar','ujarnya','umumnya','ungkap','ungkapnya','untuk','usah','usai','v','w','waduh','wah','wahai',
+    'waktunya','walau','walaupun','wong','x','y','ya','yaitu','yakin','yakni','yang','z'];
+
+// tell the world about the noise words.
+exports.words = words;

package/lib/natural/util/stopwords_no.js

@@ -39,4 +39,4 @@ var words = [
     '1', '2', '3', '4', '5', '6', '7', '8', '9', '0', '_'];
 
 // tell the world about the noise words.
-exports.words = words;
+exports.words = words;

package/lib/natural/util/stopwords_sv.js

@@ -0,0 +1,70 @@
+/*
+Copyright (c) 2017, Dogan Yazar
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+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.
+*/
+
+// a list of commonly used words that have little meaning and can be excluded
+// from analysis.
+const words = ["aderton","adertonde","adjö","aldrig","alla","allas","allt","alltid",
+"alltså","andra","andras","annan","annat","artonde","artonn","att","av","bakom",
+"bara","behöva","behövas","behövde","behövt","beslut","beslutat","beslutit","bland",
+"blev","bli","blir","blivit","bort","borta","bra","bäst","bättre","båda","bådas",
+"dag","dagar","dagarna","dagen","de","del","delen","dem","den","denna","deras",
+"dess","dessa","det","detta","dig","din","dina","dit","ditt","dock","dom","du",
+"där","därför","då","e","efter","eftersom","ej","elfte","eller","elva","emot","en",
+"enkel","enkelt","enkla","enligt","ens","er","era","ers","ert","ett","ettusen",
+"fanns","fem","femte","femtio","femtionde","femton","femtonde","fick","fin",
+"finnas","finns","fjorton","fjortonde","fjärde","fler","flera","flesta","fram",
+"framför","från","fyra","fyrtio","fyrtionde","få","får","fått","följande","för",
+"före","förlåt","förra","första","genast","genom","gick","gjorde","gjort","god",
+"goda","godare","godast","gott","gälla","gäller","gällt","gärna","gå","går","gått",
+"gör","göra","ha","hade","haft","han","hans","har","heller","hellre","helst","helt",
+"henne","hennes","hit","hon","honom","hundra","hundraen","hundraett","hur","här",
+"hög","höger","högre","högst","i","ibland","icke","idag","igen","igår","imorgon",
+"in","inför","inga","ingen","ingenting","inget","innan","inne","inom","inte",
+"inuti","ja","jag","jo","ju","just","jämfört","kan","kanske","knappast","kom",
+"komma","kommer","kommit","kr","kunde","kunna","kunnat","kvar","legat","ligga",
+"ligger","lika","likställd","likställda","lilla","lite","liten","litet","länge",
+"längre","längst","lätt","lättare","lättast","långsam","långsammare","långsammast",
+"långsamt","långt","låt","man","med","mej","mellan","men","mer","mera","mest","mig",
+"min","mina","mindre","minst","mitt","mittemot","mot","mycket","många","måste",
+"möjlig","möjligen","möjligt","möjligtvis","ned","nederst","nedersta","nedre",
+"nej","ner","ni","nio","nionde","nittio","nittionde","nitton","nittonde","nog",
+"noll","nr","nu","nummer","när","nästa","någon","någonting","något","några","nån",
+"nånting","nåt","nödvändig","nödvändiga","nödvändigt","nödvändigtvis","och","också",
+"ofta","oftast","olika","olikt","om","oss","på","rakt","redan","rätt","sa","sade",
+"sagt","samma","sedan","senare","senast","sent","sex","sextio","sextionde","sexton",
+"sextonde","sig","sin","sina","sist","sista","siste","sitt","sitta","sju","sjunde",
+"sjuttio","sjuttionde","sjutton","sjuttonde","själv","sjätte","ska","skall","skulle",
+"slutligen","små","smått","snart","som","stor","stora","stort","större","störst",
+"säga","säger","sämre","sämst","så","sådan","sådana","sådant","ta","tack","tar",
+"tidig","tidigare","tidigast","tidigt","till","tills","tillsammans","tio","tionde",
+"tjugo","tjugoen","tjugoett","tjugonde","tjugotre","tjugotvå","tjungo","tolfte",
+"tolv","tre","tredje","trettio","trettionde","tretton","trettonde","två","tvåhundra",
+"under","upp","ur","ursäkt","ut","utan","utanför","ute","va","vad","var","vara",
+"varför","varifrån","varit","varje","varken","vars","varsågod","vart","vem","vems",
+"verkligen","vi","vid","vidare","viktig","viktigare","viktigast","viktigt","vilka",
+"vilkas","vilken","vilket","vill","väl","vänster","vänstra","värre","vår","våra",
+"vårt","än","ännu","är","även","åt","åtminstone","åtta","åttio","åttionde",
+"åttonde","över","övermorgon","överst","övre", "1", "2", "3", "4", "5", "6", "7",
+"8", "9", "0"]
+
+// tell the world about the noise words.
+exports.words = words;

package/lib/natural/wordnet/wordnet_file.js

@@ -53,7 +53,13 @@ function open(callback) {
         console.log('Unable to open %s', filePath);
         return;
     }
-    callback(err, fd, function() {fs.close(fd)});
+    callback(err, fd, function() {
+      fs.close(fd, function(error) {
+        if (error) {
+          throw error;
+        }
+      })
+    });
   });
 }
 

package/lr_classifier.json

@@ -1 +1 @@
-{"classifier":{"examples":{"computing":[[1,1,0,0,0,0,0,0,0],[0,0,1,1,0,0,0,0,0],[0,0,0,1,1,1,0,0,0]],"literature":[[0,0,1,0,0,0,1,0,0],[0,0,0,0,0,0,1,1,0],[0,0,0,0,0,0,1,0,1]]},"features":[],"featurePositions":{},"maxFeaturePosition":0,"classifications":["computing","literature"],"exampleCount":6,"theta":[{"elements":[2.0057203693422903,2.0057203693422903,0.0904766662626176,3.447364098636818,0.9696521506748157,0.9696521506748157,-4.840706080886848,-1.2267353995937322,-1.2267353995937322]},{"elements":[-2.0057203693422894,-2.0057203693422894,-0.09047666626261801,-3.4473640986368186,-0.9696521506748156,-0.9696521506748156,4.84070608088685,1.2267353995937313,1.2267353995937313]}]},"docs":[{"label":"computing","text":["fix","box"]},{"label":"computing","text":["write","code"]},{"label":"computing","text":["nasti","script","code"]},{"label":"literature","text":["write","book"]},{"label":"literature","text":["read","book"]},{"label":"literature","text":["studi","book"]}],"features":{"fix":1,"box":1,"write":2,"code":2,"nasti":1,"script":1,"book":3,"read":1,"studi":1},"stemmer":{},"lastAdded":6,"events":{"domain":null,"_events":{},"_eventsCount":0}}
+{"classifier":{"examples":{"computing":[[1,1,0,0,0,0,0,0,0],[0,0,1,1,0,0,0,0,0],[0,0,0,1,1,1,0,0,0]],"literature":[[0,0,1,0,0,0,1,0,0],[0,0,0,0,0,0,1,1,0],[0,0,0,0,0,0,1,0,1]]},"features":[],"featurePositions":{},"maxFeaturePosition":0,"classifications":["computing","literature"],"exampleCount":6,"theta":[{"elements":[2.0057203693422903,2.0057203693422903,0.0904766662626176,3.447364098636818,0.9696521506748157,0.9696521506748157,-4.840706080886848,-1.2267353995937322,-1.2267353995937322]},{"elements":[-2.0057203693422894,-2.0057203693422894,-0.09047666626261801,-3.4473640986368186,-0.9696521506748156,-0.9696521506748156,4.84070608088685,1.2267353995937313,1.2267353995937313]}]},"docs":[{"label":"computing","text":["fix","box"]},{"label":"computing","text":["write","code"]},{"label":"computing","text":["nasti","script","code"]},{"label":"literature","text":["write","book"]},{"label":"literature","text":["read","book"]},{"label":"literature","text":["studi","book"]}],"features":{"fix":1,"box":1,"write":2,"code":2,"nasti":1,"script":1,"book":3,"read":1,"studi":1},"stemmer":{},"lastAdded":6,"events":{"_events":{},"_eventsCount":0}}