stopwords-filter 0.3.1 → 0.6.0

checksums.yaml

@@ -1,15 +1,7 @@
 ---
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    ODhiNzk3Y2I1OTJhNTViNjIyYmVjM2QyNjBkMzUyNDI3Y2E0NzFmNg==
-  data.tar.gz: !binary |-
-    MDU4NTU1NmEyM2VkMmE3MzExYjVhZDVlOTQ0ZjFjZTEwMWI3MDA1OQ==
+SHA1:
+  metadata.gz: f43db8de625992e54e752f11c4dec0b867356110
+  data.tar.gz: 65ce58a27b428dd485233162d136b875e14a67d9
 SHA512:
-  metadata.gz: !binary |-
-    OGFmODQ4ZDA1M2E1MWM3NmYyMmUzZTA3OTczY2U4NzdhNThiODkxNzc5ZTFl
-    MjU2M2M4ZTMyNmYzOWQzNDljMTZlNjg3MDE1M2MzNDMyNTJkN2FhNWNhZTYw
-    NDk5Yjc5NDAxMTgyOGYzYjA1MjZkNTY0MDk2MGI2Yzk4OTI0ODc=
-  data.tar.gz: !binary |-
-    ZTg1ZTlhN2QxNTViMjAyMmUyMzFjYjVhNDEyYzAzYWYxNWIxNzQxMmRlZTYz
-    OTFmOWRjOGViNWJkNmNlNDI3YTAzZmYwZGU5NzNiMDhiNGQ0NjAyNjA3MzJh
-    M2VjYTg4NWI4ZDNhOGFjOWQzM2YyNDNmMjQyZDM4MDAxMTc3MmM=
+  metadata.gz: b1fc4531396521496d8a2e27da5e3a8b695194da9def0028db4bf01421aa9a705c50ababa0ee4428f8fcec8ababcdb053cdd9654a5c8cdf7d1a4c5cce531446d
+  data.tar.gz: acc0042a007890fee128b965b0291d8b9bf3feb3cd1f2808bb19db9fe2f38ce7f5dfbb3a5d111d4b84a37c6174bc38dc2b9cb11200dee141d2b435b7f7b28315

data/CHANGELOG

@@ -1,12 +1,38 @@
-0.3.1:
-  * Added Romanian language [@MihaiValentin]
+0.6.0:
+  * Added support for: [@bettysteger] [#16]
+    * Afrikaans (af)
+    * Arabic (ar)
+    * Bengali (bn)
+    * Breton (br)
+    * Catalán (ca)
+    * Czesch (cs)
+    * Hebrew (he)
+    * Indonesian (id)
+    * Korean (ko)
+    * Thai (th)
+    * Turkish (tr)
+    * Vietnamese (vi)
+  * Added keywords for English and German [@bettysteger] [#16]
+  * Fixed upcase/downcase behaviour [@bettysteger] [#16]
+  * Added gender neutral versions of some words in spanish [@fauno] [#17]
+  * Bumped rdoc version [@dependabot] [#18]
+  * Fixed Finnish locale code from `fn` to `fi`
+0.5.0:
+  * Added Greek stopwords based on Lucene [@vrypan] [#13]
+  * Fixed CSV format for sv and ru locales [@woto] [#14]
+  * Fixed romanian and polish CSV not being included in the gemspec.
+0.4.1:
+  * Dummy version to fix metadata in gemspec
+0.4.0:
+  * Added Polish stopwords based on https://pl.wikipedia.org/wiki/Wikipedia:Stopwords [@grzegorzblaszczyk] [#9]
+  * Added info when no locale is found on snowball filter [@nerde] [#10]
 0.3.0:
-  * Added custom words list to snowball filter [@sbeckeriv]
-  * Fixed problem about initialization: https://github.com/brenes/stopwords-filter/issues/3 [@zackxu1]
+ * Added custom words list to snowball filter [@sbeckeriv]
+ * Fixed problem about initialization: https://github.com/brenes/stopwords-filter/issues/3 [@zackxu1]
 0.2.0:
-  * Added stopword? method [@s2gatev]
-  * Added Sieve class [@s2gatev]
-  * Added bulgarian language [@s2gatev]
+ * Added stopword? method [@s2gatev]
+ * Added Sieve class [@s2gatev]
+ * Added bulgarian language [@s2gatev]
 0.1.0
-  * Added simple filter [@brenes]
-  * Added snowball filter [@brenes]
+ * Added simple filter [@brenes]
+ * Added snowball filter [@brenes]

data/Gemfile

@@ -2,6 +2,6 @@
 source "https://rubygems.org"
 
 group :test do
-  gem "rspec", "2.11"
+  gem "rspec"
   gem "jeweler", "1.8.4"
 end

data/Gemfile.lock

@@ -1,29 +1,35 @@
 GEM
   remote: https://rubygems.org/
   specs:
-    diff-lcs (1.1.3)
-    git (1.2.5)
+    diff-lcs (1.3)
+    git (1.3.0)
     jeweler (1.8.4)
       bundler (~> 1.0)
       git (>= 1.2.5)
       rake
       rdoc
-    json (1.7.4)
-    rake (0.9.2.2)
-    rdoc (3.12)
-      json (~> 1.4)
-    rspec (2.11.0)
-      rspec-core (~> 2.11.0)
-      rspec-expectations (~> 2.11.0)
-      rspec-mocks (~> 2.11.0)
-    rspec-core (2.11.1)
-    rspec-expectations (2.11.2)
-      diff-lcs (~> 1.1.3)
-    rspec-mocks (2.11.2)
+    rake (13.0.3)
+    rdoc (6.3.2)
+    rspec (3.5.0)
+      rspec-core (~> 3.5.0)
+      rspec-expectations (~> 3.5.0)
+      rspec-mocks (~> 3.5.0)
+    rspec-core (3.5.4)
+      rspec-support (~> 3.5.0)
+    rspec-expectations (3.5.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.5.0)
+    rspec-mocks (3.5.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.5.0)
+    rspec-support (3.5.0)
 
 PLATFORMS
   ruby
 
 DEPENDENCIES
   jeweler (= 1.8.4)
-  rspec (= 2.11)
+  rspec
+
+BUNDLED WITH
+   1.13.6

data/README.md

@@ -1,6 +1,8 @@
 Stopwords Filter
 ================
 
+[![Build Status](https://travis-ci.org/brenes/stopwords-filter.svg?branch=master)](https://travis-ci.org/brenes/stopwords-filter)
+
 This project is a very simple and naive implementation of a stopwords filter that remove a list of banned words (stopwords) from a sentence.
 
 Quick guide
@@ -17,7 +19,8 @@ gem install stopwords-filter
 or
 
 ```
-gem 'stopwords-filter'
+# Don't forget the 'require:'
+gem 'stopwords-filter', require: 'stopwords'
 ```
 
 in your Gemfile.
@@ -104,6 +107,8 @@ That's all?
 
 I know what you're thinking, it takes a line of ruby code to filter one array from other. That's why we have added an extra functionality, [Snowball][wikipedia_snowball] stopwords lists, already built for you and ready to use.
 
+At least, in the beginning we were using snowball stopwords, but several collaborators have improved this humble gem by including new languages or adding new stopwords. So now, the Snowball version is more an "Snowball and friends" version.
+
 How do I use that snowball thing?
 ---------------------------------
 
@@ -119,6 +124,41 @@ And then you filter without worrying about the exact stopwords used
 filter.filter 'guide by douglas adams'.split  #-> ['guide', 'douglas', 'adams']
 ```
 
+Which languages are supported with snowball?
+-------------------------------------------
+
+Currently we have support for:
+
+  * Afrikaans (af)
+  * Arabic (ar)
+  * Bengali (bn)
+  * Breton (br)
+  * Catalán (ca)
+  * Czesch (cs)
+  * Danish (da)
+  * German (de)
+  * Greek (el)
+  * English (en)
+  * Spanish (es)
+  * Finnish (fi): Due to an error it can also be used referring to the `fn` locale
+  * French (fr)
+  * Hebrew (he)
+  * Hungarian (hu)
+  * Indonesian (id)
+  * Italian (it)
+  * Korean (ko)
+  * Dutch (nl)
+  * Polish (pl)
+  * Portuguese (pt)
+  * Romanian (ro)
+  * Russian (ru)
+  * Swedish (sv)
+  * Thai (th)
+  * Turkish (tr)
+  * Vietnamese (vi)
+
+In the changelog you can see the collaborators for each language.
+
 Anything else?
 --------------
 
@@ -129,6 +169,8 @@ Ackonowledgments
 
 Thanks to @s2gatev who added the `stopword?` method and the sieve class to this gem
 
+Thanks to @bettysteger, @fauno, @vrypan, @woto, @grzegorzblaszczyk, @nerde, @sbeckeriv and @zackxu1 for language support and other features.
+
   [wikipedia_stopwords]: http://en.wikipedia.org/wiki/Stopword
   [solr]: https://github.com/sunspot/sunspot
   [sphinx]: https://github.com/freelancing-god/thinking-sphinx

data/VERSION

@@ -1 +1 @@
-0.3.1
+0.6.0

data/lib/stopwords/filter.rb

@@ -5,15 +5,15 @@ module Stopwords
     attr_reader :stopwords
 
     def initialize stopwords
-      @stopwords = stopwords
+      @stopwords = stopwords.map(&:downcase)
     end
 
     def filter words
-      words - @stopwords
+      words.reject{ |word| stopword?(word) }
     end
 
     def stopword? word
-      stopwords.include? word
+      stopwords.include?(word) || stopwords.include?(word.downcase)
     end
 
   end

data/lib/stopwords/snowball/filter.rb

@@ -5,11 +5,11 @@ module Stopwords
       attr_reader :locale_filename
 
       def initialize locale, custom_list = []
-        @locale = locale
+        @locale = locale.gsub(/-\w+/, '') # remove country appendix
         @locale_filename = "#{File.dirname(__FILE__)}/locales/#{locale}.csv"
 
-        raise "Unknown locale" unless File.exists?(@locale_filename)
-        super File.read(@locale_filename).split(",") + custom_list 
+        raise ArgumentError.new("Unknown locale: #{locale.inspect}") unless File.exists?(@locale_filename)
+        super File.read(@locale_filename).split(",") + custom_list
       end
     end
   end

data/lib/stopwords/snowball/locales/af.csv

@@ -0,0 +1 @@
+die,het,en,sy,nie,was,hy,te,is,ek,om,hulle,in,my,'n,vir,toe,haar,van,dit,op,se,wat,met,gaan,baie,ons,jy,na,maar,hom,so,n,huis,kan,aan,dat,daar,sal,jou,gesê,by,kom,een,ma,as,son,groot,begin,al

data/lib/stopwords/snowball/locales/ar.csv

@@ -0,0 +1 @@
+،,آض,آمينَ,آه,آهاً,آي,أ,أب,أجل,أجمع,أخ,أخذ,أصبح,أضحى,أقبل,أقل,أكثر,ألا,أم,أما,أمامك,أمامكَ,أمسى,أمّا,أن,أنا,أنت,أنتم,أنتما,أنتن,أنتِ,أنشأ,أنّى,أو,أوشك,أولئك,أولئكم,أولاء,أولالك,أوّهْ,أي,أيا,أين,أينما,أيّ,أَنَّ,أََيُّ,أُفٍّ,إذ,إذا,إذاً,إذما,إذن,إلى,إليكم,إليكما,إليكنّ,إليكَ,إلَيْكَ,إلّا,إمّا,إن,إنّما,إي,إياك,إياكم,إياكما,إياكن,إيانا,إياه,إياها,إياهم,إياهما,إياهن,إياي,إيهٍ,إِنَّ,ا,ابتدأ,اثر,اجل,احد,اخرى,اخلولق,اذا,اربعة,ارتدّ,استحال,اطار,اعادة,اعلنت,اف,اكثر,اكد,الألاء,الألى,الا,الاخيرة,الان,الاول,الاولى,التى,التي,الثاني,الثانية,الذاتي,الذى,الذي,الذين,السابق,الف,اللائي,اللاتي,اللتان,اللتيا,اللتين,اللذان,اللذين,اللواتي,الماضي,المقبل,الوقت,الى,اليوم,اما,امام,امس,ان,انبرى,انقلب,انه,انها,او,اول,اي,ايار,ايام,ايضا,ب,بات,باسم,بان,بخٍ,برس,بسبب,بسّ,بشكل,بضع,بطآن,بعد,بعض,بك,بكم,بكما,بكن,بل,بلى,بما,بماذا,بمن,بن,بنا,به,بها,بي,بيد,بين,بَسْ,بَلْهَ,بِئْسَ,تانِ,تانِك,تبدّل,تجاه,تحوّل,تلقاء,تلك,تلكم,تلكما,تم,تينك,تَيْنِ,تِه,تِي,ثلاثة,ثم,ثمّ,ثمّة,ثُمَّ,جعل,جلل,جميع,جير,حار,حاشا,حاليا,حاي,حتى,حرى,حسب,حم,حوالى,حول,حيث,حيثما,حين,حيَّ,حَبَّذَا,حَتَّى,حَذارِ,خلا,خلال,دون,دونك,ذا,ذات,ذاك,ذانك,ذانِ,ذلك,ذلكم,ذلكما,ذلكن,ذو,ذوا,ذواتا,ذواتي,ذيت,ذينك,ذَيْنِ,ذِه,ذِي,راح,رجع,رويدك,ريث,رُبَّ,زيارة,سبحان,سرعان,سنة,سنوات,سوف,سوى,سَاءَ,سَاءَمَا,شبه,شخصا,شرع,شَتَّانَ,صار,صباح,صفر,صهٍ,صهْ,ضد,ضمن,طاق,طالما,طفق,طَق,ظلّ,عاد,عام,عاما,عامة,عدا,عدة,عدد,عدم,عسى,عشر,عشرة,علق,على,عليك,عليه,عليها,علًّ,عن,عند,عندما,عوض,عين,عَدَسْ,عَمَّا,غدا,غير,ـ,ف,فان,فلان,فو,فى,في,فيم,فيما,فيه,فيها,قال,قام,قبل,قد,قطّ,قلما,قوة,كأنّما,كأين,كأيّ,كأيّن,كاد,كان,كانت,كذا,كذلك,كرب,كل,كلا,كلاهما,كلتا,كلم,كليكما,كليهما,كلّما,كلَّا,كم,كما,كي,كيت,كيف,كيفما,كَأَنَّ,كِخ,لئن,لا,لات,لاسيما,لدن,لدى,لعمر,لقاء,لك,لكم,لكما,لكن,لكنَّما,لكي,لكيلا,للامم,لم,لما,لمّا,لن,لنا,له,لها,لو,لوكالة,لولا,لوما,لي,لَسْتَ,لَسْتُ,لَسْتُم,لَسْتُمَا,لَسْتُنَّ,لَسْتِ,لَسْنَ,لَعَلَّ,لَكِنَّ,لَيْتَ,لَيْسَ,لَيْسَا,لَيْسَتَا,لَيْسَتْ,لَيْسُوا,لَِسْنَا,ما,ماانفك,مابرح,مادام,ماذا,مازال,مافتئ,مايو,متى,مثل,مذ,مساء,مع,معاذ,مقابل,مكانكم,مكانكما,مكانكنّ,مكانَك,مليار,مليون,مما,ممن,من,منذ,منها,مه,مهما,مَنْ,مِن,نحن,نحو,نعم,نفس,نفسه,نهاية,نَخْ,نِعِمّا,نِعْمَ,ها,هاؤم,هاكَ,هاهنا,هبّ,هذا,هذه,هكذا,هل,هلمَّ,هلّا,هم,هما,هن,هنا,هناك,هنالك,هو,هي,هيا,هيت,هيّا,هَؤلاء,هَاتانِ,هَاتَيْنِ,هَاتِه,هَاتِي,هَجْ,هَذا,هَذانِ,هَذَيْنِ,هَذِه,هَذِي,هَيْهَاتَ,و,و6,وا,واحد,واضاف,واضافت,واكد,وان,واهاً,واوضح,وراءَك,وفي,وقال,وقالت,وقد,وقف,وكان,وكانت,ولا,ولم,ومن,وهو,وهي,ويكأنّ,وَيْ,وُشْكَانََ,يكون,يمكن,يوم,ّأيّان

data/lib/stopwords/snowball/locales/bn.csv

@@ -0,0 +1 @@
+অতএব,অথচ,অথবা,অনুযায়ী,অনেক,অনেকে,অনেকেই,অন্তত,অন্য,অবধি,অবশ্য,অর্থাত,আই,আগামী,আগে,আগেই,আছে,আজ,আদ্যভাগে,আপনার,আপনি,আবার,আমরা,আমাকে,আমাদের,আমার,আমি,আর,আরও,ই,ইত্যাদি,ইহা,উচিত,উত্তর,উনি,উপর,উপরে,এ,এঁদের,এঁরা,এই,একই,একটি,একবার,একে,এক্,এখন,এখনও,এখানে,এখানেই,এটা,এটাই,এটি,এত,এতটাই,এতে,এদের,এব,এবং,এবার,এমন,এমনকী,এমনি,এর,এরা,এল,এস,এসে,ঐ,ও,ওঁদের,ওঁর,ওঁরা,ওই,ওকে,ওখানে,ওদের,ওর,ওরা,কখনও,কত,কবে,কমনে,কয়েক,কয়েকটি,করছে,করছেন,করতে,করবে,করবেন,করলে,করলেন,করা,করাই,করায়,করার,করি,করিতে,করিয়া,করিয়ে,করে,করেই,করেছিলেন,করেছে,করেছেন,করেন,কাউকে,কাছ,কাছে,কাজ,কাজে,কারও,কারণ,কি,কিংবা,কিছু,কিছুই,কিন্তু,কী,কে,কেউ,কেউই,কেখা,কেন,কোটি,কোন,কোনও,কোনো,ক্ষেত্রে,কয়েক,খুব,গিয়ে,গিয়েছে,গিয়ে,গুলি,গেছে,গেল,গেলে,গোটা,চলে,চান,চায়,চার,চালু,চেয়ে,চেষ্টা,ছাড়া,ছাড়াও,ছিল,ছিলেন,জন,জনকে,জনের,জন্য,জন্যওজে,জানতে,জানা,জানানো,জানায়,জানিয়ে,জানিয়েছে,জে,জ্নজন,টি,ঠিক,তখন,তত,তথা,তবু,তবে,তা,তাঁকে,তাঁদের,তাঁর,তাঁরা,তাঁাহারা,তাই,তাও,তাকে,তাতে,তাদের,তার,তারপর,তারা,তারৈ,তাহলে,তাহা,তাহাতে,তাহার,তিনঐ,তিনি,তিনিও,তুমি,তুলে,তেমন,তো,তোমার,থাকবে,থাকবেন,থাকা,থাকায়,থাকে,থাকেন,থেকে,থেকেই,থেকেও,দিকে,দিতে,দিন,দিয়ে,দিয়েছে,দিয়েছেন,দিলেন,দু,দুই,দুটি,দুটো,দেওয়া,দেওয়ার,দেওয়া,দেখতে,দেখা,দেখে,দেন,দেয়,দ্বারা,ধরা,ধরে,ধামার,নতুন,নয়,না,নাই,নাকি,নাগাদ,নানা,নিজে,নিজেই,নিজেদের,নিজের,নিতে,নিয়ে,নিয়ে,নেই,নেওয়া,নেওয়ার,নেওয়া,নয়,পক্ষে,পর,পরে,পরেই,পরেও,পর্যন্ত,পাওয়া,পাচ,পারি,পারে,পারেন,পি,পেয়ে,পেয়্র্,প্রতি,প্রথম,প্রভৃতি,প্রযন্ত,প্রাথমিক,প্রায়,প্রায়,ফলে,ফিরে,ফের,বক্তব্য,বদলে,বন,বরং,বলতে,বলল,বললেন,বলা,বলে,বলেছেন,বলেন,বসে,বহু,বা,বাদে,বার,বি,বিনা,বিভিন্ন,বিশেষ,বিষয়টি,বেশ,বেশি,ব্যবহার,ব্যাপারে,ভাবে,ভাবেই,মতো,মতোই,মধ্যভাগে,মধ্যে,মধ্যেই,মধ্যেও,মনে,মাত্র,মাধ্যমে,মোট,মোটেই,যখন,যত,যতটা,যথেষ্ট,যদি,যদিও,যা,যাঁর,যাঁরা,যাওয়া,যাওয়ার,যাওয়া,যাকে,যাচ্ছে,যাতে,যাদের,যান,যাবে,যায়,যার,যারা,যিনি,যে,যেখানে,যেতে,যেন,যেমন,র,রকম,রয়েছে,রাখা,রেখে,লক্ষ,শুধু,শুরু,সঙ্গে,সঙ্গেও,সব,সবার,সমস্ত,সম্প্রতি,সহ,সহিত,সাধারণ,সামনে,সি,সুতরাং,সে,সেই,সেখান,সেখানে,সেটা,সেটাই,সেটাও,সেটি,স্পষ্ট,স্বয়ং,হইতে,হইবে,হইয়া,হওয়া,হওয়ায়,হওয়ার,হচ্ছে,হত,হতে,হতেই,হন,হবে,হবেন,হয়,হয়তো,হয়নি,হয়ে,হয়েই,হয়েছিল,হয়েছে,হয়েছেন,হল,হলে,হলেই,হলেও,হলো,হাজার,হিসাবে,হৈলে,হোক,হয়

data/lib/stopwords/snowball/locales/br.csv

@@ -0,0 +1 @@
+a,ainda,alem,ambas,ambos,antes,ao,aonde,aos,apos,aquele,aqueles,as,assim,com,como,contra,contudo,cuja,cujas,cujo,cujos,da,das,de,dela,dele,deles,demais,depois,desde,desta,deste,dispoe,dispoem,diversa,diversas,diversos,do,dos,durante,e,ela,elas,ele,eles,em,entao,entre,essa,essas,esse,esses,esta,estas,este,estes,ha,isso,isto,logo,mais,mas,mediante,menos,mesma,mesmas,mesmo,mesmos,na,nao,nas,nem,nesse,neste,nos,o,os,ou,outra,outras,outro,outros,pelas,pelo,pelos,perante,pois,por,porque,portanto,propios,proprio,quais,qual,qualquer,quando,quanto,que,quem,quer,se,seja,sem,sendo,seu,seus,sob,sobre,sua,suas,tal,tambem,teu,teus,toda,todas,todo,todos,tua,tuas,tudo,um,uma,umas,uns

data/lib/stopwords/snowball/locales/ca.csv

@@ -0,0 +1 @@
+a,abans,ací,ah,així,això,al,aleshores,algun,alguna,algunes,alguns,alhora,allà,allí,allò,als,altra,altre,altres,amb,ambdues,ambdós,apa,aquell,aquella,aquelles,aquells,aquest,aquesta,aquestes,aquests,aquí,baix,cada,cadascuna,cadascunes,cadascuns,cadascú,com,contra,d'un,d'una,d'unes,d'uns,dalt,de,del,dels,des,després,dins,dintre,donat,doncs,durant,e,eh,el,els,em,en,encara,ens,entre,eren,es,esta,estaven,esteu,està,estàvem,estàveu,et,etc,ets,fins,fora,gairebé,ha,han,has,havia,he,hem,heu,hi,ho,i,igual,iguals,ja,l'hi,la,les,li,li'n,llavors,m'he,ma,mal,malgrat,mateix,mateixa,mateixes,mateixos,me,mentre,meu,meus,meva,meves,molt,molta,moltes,molts,mon,mons,més,n'he,n'hi,ne,ni,no,nogensmenys,només,nosaltres,nostra,nostre,nostres,o,oh,oi,on,pas,pel,pels,per,perquè,però,poc,poca,pocs,poques,potser,propi,qual,quals,quan,quant,que,quelcom,qui,quin,quina,quines,quins,què,s'ha,s'han,sa,semblant,semblants,ses,seu,seus,seva,seves,si,sobre,sobretot,solament,sols,son,sons,sota,sou,sóc,són,t'ha,t'han,t'he,ta,tal,també,tampoc,tan,tant,tanta,tantes,teu,teus,teva,teves,ton,tons,tot,tota,totes,tots,un,una,unes,uns,us,va,vaig,vam,van,vas,veu,vosaltres,vostra,vostre,vostres,érem,éreu,és

data/lib/stopwords/snowball/locales/cs.csv

@@ -0,0 +1 @@
+a,aby,ahoj,aj,ale,anebo,ani,ano,asi,aspoň,atd,atp,ačkoli,až,bez,beze,blízko,bohužel,brzo,bude,budem,budeme,budete,budeš,budou,budu,by,byl,byla,byli,bylo,byly,bys,být,během,chce,chceme,chcete,chceš,chci,chtít,chtějí,chut',chuti,co,což,cz,daleko,další,den,deset,devatenáct,devět,dnes,do,dobrý,docela,dva,dvacet,dvanáct,dvě,dál,dále,děkovat,děkujeme,děkuji,ho,hodně,i,jak,jakmile,jako,jakož,jde,je,jeden,jedenáct,jedna,jedno,jednou,jedou,jeho,jehož,jej,jejich,její,jelikož,jemu,jen,jenom,jestli,jestliže,ještě,jež,ji,jich,jimi,jinak,jiné,již,jsem,jseš,jsi,jsme,jsou,jste,já,jí,jím,jíž,k,kam,kde,kdo,kdy,když,ke,kolik,kromě,kterou,která,které,který,kteří,kvůli,mají,mezi,mi,mne,mnou,mně,moc,mohl,mohou,moje,moji,možná,musí,my,má,málo,mám,máme,máte,máš,mé,mí,mít,mě,můj,může,na,nad,nade,napište,naproti,načež,naše,naši,ne,nebo,nebyl,nebyla,nebyli,nebyly,nedělají,nedělá,nedělám,neděláme,neděláte,neděláš,neg,nejsi,nejsou,nemají,nemáme,nemáte,neměl,není,nestačí,nevadí,než,nic,nich,nimi,nové,nový,nula,nám,námi,nás,náš,ním,ně,něco,nějak,někde,někdo,němu,němuž,o,od,ode,on,ona,oni,ono,ony,osm,osmnáct,pak,patnáct,po,pod,podle,pokud,potom,pouze,pozdě,pořád,pravé,pro,prostě,prosím,proti,proto,protože,proč,první,pta,pět,před,přes,přese,při,přičemž,re,rovně,s,se,sedm,sedmnáct,si,skoro,smí,smějí,snad,spolu,sta,sto,strana,sté,své,svých,svým,svými,ta,tady,tak,takhle,taky,také,takže,tam,tamhle,tamhleto,tamto,tato,tebe,tebou,ted',tedy,ten,tento,teto,ti,tipy,tisíc,tisíce,to,tobě,tohle,toho,tohoto,tom,tomto,tomu,tomuto,toto,trošku,tu,tuto,tvoje,tvá,tvé,tvůj,ty,tyto,téma,tím,tímto,tě,těm,těmu,třeba,tři,třináct,u,určitě,už,v,vaše,vaši,ve,vedle,večer,vlastně,vy,vám,vámi,vás,váš,více,však,všechno,všichni,vůbec,vždy,z,za,zatímco,zač,zda,zde,ze,zprávy,zpět,čau,či,článku,články,čtrnáct,čtyři,šest,šestnáct,že

data/lib/stopwords/snowball/locales/de.csv

@@ -1 +1 @@
-aber,alle,allem,allen,aller,alles,als,also,am,an,ander,andere,anderem,anderen,anderer,anderes,anderm,andern,anderr,anders,auch,auf,aus,bei,bin,bis,bist,da,damit,dann,der,den,des,dem,die,das,daß,derselbe,derselben,denselben,desselben,demselben,dieselbe,dieselben,dasselbe,dazu,dein,deine,deinem,deinen,deiner,deines,denn,derer,dessen,dich,dir,du,dies,diese,diesem,diesen,dieser,dieses,doch,dort,durch,ein,eine,einem,einen,einer,eines,einig,einige,einigem,einigen,einiger,einiges,einmal,er,ihn,ihm,es,etwas,euer,eure,eurem,euren,eurer,eures,für,gegen,gewesen,hab,habe,haben,hat,hatte,hatten,hier,hin,hinter,ich,mich,mir,ihr,ihre,ihrem,ihren,ihrer,ihres,euch,im,in,indem,ins,ist,jede,jedem,jeden,jeder,jedes,jene,jenem,jenen,jener,jenes,jetzt,kann,kein,keine,keinem,keinen,keiner,keines,können,könnte,machen,man,manche,manchem,manchen,mancher,manches,mein,meine,meinem,meinen,meiner,meines,mit,muss,musste,nach,nicht,nichts,noch,nun,nur,ob,oder,ohne,sehr,sein,seine,seinem,seinen,seiner,seines,selbst,sich,sie,ihnen,sind,so,solche,solchem,solchen,solcher,solches,soll,sollte,sondern,sonst,über,um,und,uns,unse,unsem,unsen,unser,unses,unter,viel,vom,von,vor,während,war,waren,warst,was,weg,weil,weiter,welche,welchem,welchen,welcher,welches,wenn,werde,werden,wie,wieder,will,wir,wird,wirst,wo,wollen,wollte,würde,würden,zu,zum,zur,zwar,zwischen
+a,ab,aber,ach,acht,achte,achten,achter,achtes,ag,alle,allein,allem,allen,aller,allerdings,alles,allgemeinen,als,also,am,an,ander,andere,anderem,anderen,anderer,anderes,anderm,andern,anderr,anders,au,auch,auf,aus,ausser,ausserdem,außer,außerdem,b,bald,bei,beide,beiden,beim,beispiel,bekannt,bereits,besonders,besser,besten,bin,bis,bisher,bist,c,d,d.h,da,dabei,dadurch,dafür,dagegen,daher,dahin,dahinter,damals,damit,danach,daneben,dank,dann,daran,darauf,daraus,darf,darfst,darin,darum,darunter,darüber,das,dasein,daselbst,dass,dasselbe,davon,davor,dazu,dazwischen,daß,dein,deine,deinem,deinen,deiner,deines,dem,dementsprechend,demgegenüber,demgemäss,demgemäß,demselben,demzufolge,den,denen,denn,denselben,der,deren,derer,derjenige,derjenigen,dermassen,dermaßen,derselbe,derselben,des,deshalb,desselben,dessen,deswegen,dich,die,diejenige,diejenigen,dies,diese,dieselbe,dieselben,diesem,diesen,dieser,dieses,dir,doch,dort,drei,drin,dritte,dritten,dritter,drittes,du,durch,durchaus,durfte,durften,dürfen,dürft,e,eben,ebenso,ehrlich,ei,ei,,eigen,eigene,eigenen,eigener,eigenes,ein,einander,eine,einem,einen,einer,eines,einig,einige,einigem,einigen,einiger,einiges,einmal,eins,elf,en,ende,endlich,entweder,er,ernst,erst,erste,ersten,erster,erstes,es,etwa,etwas,euch,euer,eure,eurem,euren,eurer,eures,f,folgende,früher,fünf,fünfte,fünften,fünfter,fünftes,für,g,gab,ganz,ganze,ganzen,ganzer,ganzes,gar,gedurft,gegen,gegenüber,gehabt,gehen,geht,gekannt,gekonnt,gemacht,gemocht,gemusst,genug,gerade,gern,gesagt,geschweige,gewesen,gewollt,geworden,gibt,ging,gleich,gott,gross,grosse,grossen,grosser,grosses,groß,große,großen,großer,großes,gut,gute,guter,gutes,h,hab,habe,haben,habt,hast,hat,hatte,hatten,hattest,hattet,heisst,her,heute,hier,hin,hinter,hoch,hätte,hätten,i,ich,ihm,ihn,ihnen,ihr,ihre,ihrem,ihren,ihrer,ihres,im,immer,in,indem,infolgedessen,ins,irgend,ist,j,ja,jahr,jahre,jahren,je,jede,jedem,jeden,jeder,jedermann,jedermanns,jedes,jedoch,jemand,jemandem,jemanden,jene,jenem,jenen,jener,jenes,jetzt,k,kam,kann,kannst,kaum,kein,keine,keinem,keinen,keiner,keines,kleine,kleinen,kleiner,kleines,kommen,kommt,konnte,konnten,kurz,können,könnt,könnte,l,lang,lange,leicht,leide,lieber,los,m,machen,macht,machte,mag,magst,mahn,mal,man,manche,manchem,manchen,mancher,manches,mann,mehr,mein,meine,meinem,meinen,meiner,meines,mensch,menschen,mich,mir,mit,mittel,mochte,mochten,morgen,muss,musst,musste,mussten,muß,mußt,möchte,mögen,möglich,mögt,müssen,müsst,müßt,n,na,nach,nachdem,nahm,natürlich,neben,nein,neue,neuen,neun,neunte,neunten,neunter,neuntes,nicht,nichts,nie,niemand,niemandem,niemanden,noch,nun,nur,o,ob,oben,oder,offen,oft,ohne,ordnung,p,q,r,recht,rechte,rechten,rechter,rechtes,richtig,rund,s,sa,sache,sagt,sagte,sah,satt,schlecht,schluss,schon,sechs,sechste,sechsten,sechster,sechstes,sehr,sei,seid,seien,sein,seine,seinem,seinen,seiner,seines,seit,seitdem,selbst,sich,sie,sieben,siebente,siebenten,siebenter,siebentes,sind,so,solang,solche,solchem,solchen,solcher,solches,soll,sollen,sollst,sollt,sollte,sollten,sondern,sonst,soweit,sowie,später,startseite,statt,steht,suche,t,tag,tage,tagen,tat,teil,tel,tritt,trotzdem,tun,u,uhr,um,und,und?,uns,unse,unsem,unsen,unser,unsere,unserer,unses,unter,v,vergangenen,viel,viele,vielem,vielen,vielleicht,vier,vierte,vierten,vierter,viertes,vom,von,vor,w,wahr?,wann,war,waren,warst,wart,warum,was,weg,wegen,weil,weit,weiter,weitere,weiteren,weiteres,welche,welchem,welchen,welcher,welches,wem,wen,wenig,wenige,weniger,weniges,wenigstens,wenn,wer,werde,werden,werdet,weshalb,wessen,wie,wieder,wieso,will,willst,wir,wird,wirklich,wirst,wissen,wo,woher,wohin,wohl,wollen,wollt,wollte,wollten,worden,wurde,wurden,während,währenddem,währenddessen,wäre,würde,würden,x,y,z,z.b,zehn,zehnte,zehnten,zehnter,zehntes,zeit,zu,zuerst,zugleich,zum,zunächst,zur,zurück,zusammen,zwanzig,zwar,zwei,zweite,zweiten,zweiter,zweites,zwischen,zwölf,über,überhaupt,übrigens

data/lib/stopwords/snowball/locales/el.csv

@@ -0,0 +1 @@
+ο,η,το,οι,τα,του,τησ,των,τον,την,και,κι,κ,ειμαι,εισαι,ειναι,ειμαστε,ειστε,στο,στον,στη,στην,μα,αλλα,απο,για,προσ,με,σε,ωσ,παρα,αντι,κατα,μετα,θα,να,δε,δεν,μη,μην,επι,ενω,εαν,αν,τοτε,που,πωσ,ποιοσ,ποια,ποιο,ποιοι,ποιεσ,ποιων,ποιουσ,αυτοσ,αυτη,αυτο,αυτοι,αυτων,αυτουσ,αυτεσ,αυτα,εκεινοσ,εκεινη,εκεινο,εκεινοι,εκεινεσ,εκεινα,εκεινων,εκεινουσ,οπωσ,ομωσ,ισωσ,οσο,οτι

data/lib/stopwords/snowball/locales/en.csv

@@ -1 +1 @@
-i,me,my,myself,we,our,ours,ourselves,you,your,yours,yourself,yourselves,he,him,his,himself,she,her,hers,herself,it,its,itself,they,them,their,theirs,themselves,what,which,who,whom,this,that,these,those,am,is,are,was,were,be,been,being,have,has,had,having,do,does,did,doing,would,should,could,ought,i'm,you're,he's,she's,it's,we're,they're,i've,you've,we've,they've,i'd,you'd,he'd,she'd,we'd,they'd,i'll,you'll,he'll,she'll,we'll,they'll,isn't,aren't,wasn't,weren't,hasn't,haven't,hadn't,doesn't,don't,didn't,won't,wouldn't,shan't,shouldn't,can't,cannot,couldn't,mustn't,let's,that's,who's,what's,here's,there's,when's,where's,why's,how's,a,an,the,and,but,if,or,because,as,until,while,of,at,by,for,with,about,against,between,into,through,during,before,after,above,below,to,from,up,down,in,out,on,off,over,under,again,further,then,once,here,there,when,where,why,how,all,any,both,each,few,more,most,other,some,such,no,nor,not,only,own,same,so,than,too,very
+i,me,my,myself,we,our,ours,ourselves,you,your,yours,yourself,yourselves,he,him,his,himself,she,her,hers,herself,it,its,itself,they,them,their,theirs,themselves,what,which,who,whom,this,that,these,those,am,is,are,was,were,be,been,being,have,has,had,having,do,does,did,doing,would,should,could,ought,i'm,you're,he's,she's,it's,we're,they're,i've,you've,we've,they've,i'd,you'd,he'd,she'd,we'd,they'd,i'll,you'll,he'll,she'll,we'll,they'll,isn't,aren't,wasn't,weren't,hasn't,haven't,hadn't,doesn't,don't,didn't,won't,wouldn't,shan't,shouldn't,can't,cannot,couldn't,mustn't,let's,that's,who's,what's,here's,there's,when's,where's,why's,how's,a,an,the,and,but,if,or,because,as,until,while,of,at,by,for,with,about,against,between,into,through,during,before,after,above,below,to,from,up,down,in,out,on,off,over,under,again,further,then,once,here,there,when,where,why,how,all,any,both,each,few,more,most,other,some,such,no,nor,not,only,own,same,so,than,too,very,us,really,also,already,even,altough,much,bit,many

data/lib/stopwords/snowball/locales/es.csv

@@ -1 +1 @@
-de,la,que,el,en,y,a,los,del,se,las,por,un,para,con,no,una,su,al,lo,como,más,pero,sus,le,ya,o,este,sí,porque,esta,entre,cuando,muy,sin,sobre,también,me,hasta,hay,donde,quien,desde,todo,nos,durante,todos,uno,les,ni,contra,otros,ese,eso,ante,ellos,e,esto,mí,antes,algunos,qué,unos,yo,otro,otras,otra,él,tanto,esa,estos,mucho,quienes,nada,muchos,cual,poco,ella,estar,estas,algunas,algo,nosotros,mi,mis,tú,te,ti,tu,tus,ellas,nosotras,vosotros,vosotras,os,mío,mía,míos,mías,tuyo,tuya,tuyos,tuyas,suyo,suya,suyos,suyas,nuestro,nuestra,nuestros,nuestras,vuestro,vuestra,vuestros,vuestras,esos,esas,estoy,estás,está,estamos,estáis,están,esté,estés,estemos,estéis,estén,estaré,estarás,estará,estaremos,estaréis,estarán,estaría,estarías,estaríamos,estaríais,estarían,estaba,estabas,estábamos,estabais,estaban,estuve,estuviste,estuvo,estuvimos,estuvisteis,estuvieron,estuviera,estuvieras,estuviéramos,estuvierais,estuvieran,estuviese,estuvieses,estuviésemos,estuvieseis,estuviesen,estando,estado,estada,estados,estadas,estad,he,has,ha,hemos,habéis,han,haya,hayas,hayamos,hayáis,hayan,habré,habrás,habrá,habremos,habréis,habrán,habría,habrías,habríamos,habríais,habrían,había,habías,habíamos,habíais,habían,hube,hubiste,hubo,hubimos,hubisteis,hubieron,hubiera,hubieras,hubiéramos,hubierais,hubieran,hubiese,hubieses,hubiésemos,hubieseis,hubiesen,habiendo,habido,habida,habidos,habidas,soy,eres,es,somos,sois,son,sea,seas,seamos,seáis,sean,seré,serás,será,seremos,seréis,serán,sería,serías,seríamos,seríais,serían,era,eras,éramos,erais,eran,fui,fuiste,fue,fuimos,fuisteis,fueron,fuera,fueras,fuéramos,fuerais,fueran,fuese,fueses,fuésemos,fueseis,fuesen,siendo,sido,tengo,tienes,tiene,tenemos,tenéis,tienen,tenga,tengas,tengamos,tengáis,tengan,tendré,tendrás,tendrá,tendremos,tendréis,tendrán,tendría,tendrías,tendríamos,tendríais,tendrían,tenía,tenías,teníamos,teníais,tenían,tuve,tuviste,tuvo,tuvimos,tuvisteis,tuvieron,tuviera,tuvieras,tuviéramos,tuvierais,tuvieran,tuviese,tuvieses,tuviésemos,tuvieseis,tuviesen,teniendo,tenido,tenida,tenidos,tenidas,tened
+de,la,que,el,en,y,a,los,del,se,las,por,un,para,con,no,una,su,al,lo,como,más,pero,sus,le,ya,o,este,sí,porque,esta,entre,cuando,muy,sin,sobre,también,me,hasta,hay,donde,quien,desde,todo,nos,durante,todos,uno,les,ni,contra,otros,ese,eso,ante,ellos,e,esto,mí,antes,algunos,qué,unos,yo,otro,otras,otra,él,tanto,esa,estos,mucho,quienes,nada,muchos,cual,poco,ella,estar,estas,algunas,algo,nosotros,mi,mis,tú,te,ti,tu,tus,ellas,nosotras,vosotros,vosotras,os,mío,mía,míos,mías,tuyo,tuya,tuyos,tuyas,suyo,suya,suyos,suyas,nuestro,nuestra,nuestros,nuestras,vuestro,vuestra,vuestros,vuestras,esos,esas,estoy,estás,está,estamos,estáis,están,esté,estés,estemos,estéis,estén,estaré,estarás,estará,estaremos,estaréis,estarán,estaría,estarías,estaríamos,estaríais,estarían,estaba,estabas,estábamos,estabais,estaban,estuve,estuviste,estuvo,estuvimos,estuvisteis,estuvieron,estuviera,estuvieras,estuviéramos,estuvierais,estuvieran,estuviese,estuvieses,estuviésemos,estuvieseis,estuviesen,estando,estada,estadas,estad,he,has,ha,hemos,habéis,han,haya,hayas,hayamos,hayáis,hayan,habré,habrás,habrá,habremos,habréis,habrán,habría,habrías,habríamos,habríais,habrían,había,habías,habíamos,habíais,habían,hube,hubiste,hubo,hubimos,hubisteis,hubieron,hubiera,hubieras,hubiéramos,hubierais,hubieran,hubiese,hubieses,hubiésemos,hubieseis,hubiesen,habiendo,habido,habida,habidos,habidas,soy,eres,es,somos,sois,son,sea,seas,seamos,seáis,sean,seré,serás,será,seremos,seréis,serán,sería,serías,seríamos,seríais,serían,era,eras,éramos,erais,eran,fui,fuiste,fue,fuimos,fuisteis,fueron,fuera,fueras,fuéramos,fuerais,fueran,fuese,fueses,fuésemos,fueseis,fuesen,siendo,sido,tengo,tienes,tiene,tenemos,tenéis,tienen,tenga,tengas,tengamos,tengáis,tengan,tendré,tendrás,tendrá,tendremos,tendréis,tendrán,tendría,tendrías,tendríamos,tendríais,tendrían,tenía,tenías,teníamos,teníais,tenían,tuve,tuviste,tuvo,tuvimos,tuvisteis,tuvieron,tuviera,tuvieras,tuviéramos,tuvierais,tuvieran,tuviese,tuvieses,tuviésemos,tuvieseis,tuviesen,teniendo,tenido,tenida,tenidos,tenidas,tened,algunes,algunxs,elle,ellx,elles,ellxs,ese,esx,eses,esxs,estes,este,estxs,estx,lx,le,lxs,les,mucha,muchas,muches,muchxs,míe,míes,míx,míxs,nosotres,nosotrxs,nuestre,nuestres,nuestrx,nuestrxs,otre,otrx,otres,otrxs,poca,poque,pocx,suye,suyx,suyes,suyxs,tantas,tantxs,tantes,tenide,tenides,tenidx,tenidxs,toda,todas,tode,todes,todx,todxs,tuye,tuyes,tuyx,tuyxs,une,unx,unxs,unes,vosotrxs,vosotres,vuestre,vuestres,vuestrx,vuestrxs

data/lib/stopwords/snowball/locales/fi.csv

@@ -0,0 +1 @@
+olla,olen,olet,on,olemme,olette,ovat,ole,oli,olisi,olisit,olisin,olisimme,olisitte,olisivat,olit,olin,olimme,olitte,olivat,ollut,olleet,en,et,ei,emme,ette,eivät,minä,minun,minut,minua,minussa,minusta,minuun,minulla,minulta,minulle,sinä,sinun,sinut,sinua,sinussa,sinusta,sinuun,sinulla,sinulta,sinulle,hän,hänen,hänet,häntä,hänessä,hänestä,häneen,hänellä,häneltä,hänelle,me,meidän,meidät,meitä,meissä,meistä,meihin,meillä,meiltä,meille,te,teidän,teidät,teitä,teissä,teistä,teihin,teillä,teiltä,teille,he,heidän,heidät,heitä,heissä,heistä,heihin,heillä,heiltä,heille,tämä,tämän,tätä,tässä,tästä,tähän,tällä,tältä,tälle,tänä,täksi,tuo,tuon,tuota,tuossa,tuosta,tuohon,tuolla,tuolta,tuolle,tuona,tuoksi,se,sen,sitä,siinä,siitä,siihen,sillä,siltä,sille,sinä,siksi,nämä,näiden,näitä,näissä,näistä,näihin,näillä,näiltä,näille,näinä,näiksi,nuo,noiden,noita,noissa,noista,noihin,noilla,noilta,noille,noina,noiksi,ne,niiden,niitä,niissä,niistä,niihin,niillä,niiltä,niille,niinä,niiksi,kuka,kenen,kenet,ketä,kenessä,kenestä,keneen,kenellä,keneltä,kenelle,kenenä,keneksi,ketkä,keiden,ketkä,keitä,keissä,keistä,keihin,keillä,keiltä,keille,keinä,keiksi,mikä,minkä,minkä,mitä,missä,mistä,mihin,millä,miltä,mille,minä,miksi,mitkä,joka,jonka,jota,jossa,josta,johon,jolla,jolta,jolle,jona,joksi,jotka,joiden,joita,joissa,joista,joihin,joilla,joilta,joille,joina,joiksi,että,ja,jos,koska,kuin,mutta,niin,sekä,sillä,tai,vaan,vai,vaikka,kanssa,mukaan,noin,poikki,yli,kun,niin,nyt,itse

data/lib/stopwords/snowball/locales/fn.csv

@@ -0,0 +1 @@
+lib/stopwords/snowball/locales/fi.csv

data/lib/stopwords/snowball/locales/he.csv

@@ -0,0 +1 @@
+אבל,או,אולי,אותה,אותו,אותי,אותך,אותם,אותן,אותנו,אז,אחר,אחרות,אחרי,אחריכן,אחרים,אחרת,אי,איזה,איך,אין,איפה,איתה,איתו,איתי,איתך,איתכם,איתכן,איתם,איתן,איתנו,אך,אל,אלה,אלו,אם,אנחנו,אני,אס,אף,אצל,אשר,את,אתה,אתכם,אתכן,אתם,אתן,באיזומידה,באמצע,באמצעות,בגלל,בין,בלי,במידה,במקוםשבו,ברם,בשביל,בשעהש,בתוך,גם,דרך,הוא,היא,היה,היכן,היתה,היתי,הם,הן,הנה,הסיבהשבגללה,הרי,ואילו,ואת,זאת,זה,זות,יהיה,יוכל,יוכלו,יותרמדי,יכול,יכולה,יכולות,יכולים,יכל,יכלה,יכלו,יש,כאן,כאשר,כולם,כולן,כזה,כי,כיצד,כך,ככה,כל,כלל,כמו,כן,כפי,כש,לא,לאו,לאיזותכלית,לאן,לבין,לה,להיות,להם,להן,לו,לי,לכם,לכן,למה,למטה,למעלה,למקוםשבו,למרות,לנו,לעבר,לעיכן,לפיכך,לפני,מאד,מאחורי,מאיזוסיבה,מאין,מאיפה,מבלי,מבעד,מדוע,מה,מהיכן,מול,מחוץ,מי,מכאן,מכיוון,מלבד,מן,מנין,מסוגל,מעט,מעטים,מעל,מצד,מקוםבו,מתחת,מתי,נגד,נגר,נו,עד,עז,על,עלי,עליה,עליהם,עליהן,עליו,עליך,עליכם,עלינו,עם,עצמה,עצמהם,עצמהן,עצמו,עצמי,עצמם,עצמן,עצמנו,פה,רק,שוב,של,שלה,שלהם,שלהן,שלו,שלי,שלך,שלכה,שלכם,שלכן,שלנו,שם,תהיה,תחת

data/lib/stopwords/snowball/locales/id.csv

@@ -0,0 +1 @@
+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,artinya,asal,asalkan,atas,atau,ataukah,ataupun,awal,awalnya,bagai,bagaikan,bagaimana,bagaimanakah,bagaimanapun,bagi,bagian,bahkan,bahwa,bahwasanya,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,cara,caranya,cukup,cukupkah,cukuplah,cuma,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,dulu,empat,enggak,enggaknya,entah,entahlah,guna,gunakan,hal,hampir,hanya,hanyalah,harus,haruslah,harusnya,hendak,hendaklah,hendaknya,hingga,ia,ialah,ibarat,ibaratkan,ibaratnya,ikut,ingat,ingat-ingat,ingin,inginkah,inginkan,ini,inikah,inilah,itu,itukah,itulah,jadi,jadilah,jadinya,jangan,jangankan,janganlah,jauh,jawab,jawaban,jawabnya,jelas,jelaskan,jelaslah,jelasnya,jika,jikalau,juga,jumlah,jumlahnya,justru,kala,kalau,kalaulah,kalaupun,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,kenapa,kepada,kepadanya,kesampaian,keseluruhan,keseluruhannya,keterlaluan,ketika,khususnya,kini,kinilah,kira,kira-kira,kiranya,kita,kitalah,kok,kurang,lagi,lagian,lah,lain,lainnya,lalu,lama,lamanya,lanjut,lanjutnya,lebih,lewat,lima,luar,macam,maka,makanya,makin,malah,malahan,mampu,mampukah,mana,manakala,manalagi,masa,masalah,masalahnya,masih,masihkah,masing,masing-masing,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,mula,mulai,mulailah,mulanya,mungkin,mungkinkah,nah,naik,namun,nanti,nantinya,nyaris,nyatanya,oleh,olehnya,pada,padahal,padanya,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,rasa,rasanya,rata,rupanya,saat,saatnya,saja,sajalah,saling,sama,sama-sama,sambil,sampai,sampai-sampai,sampaikan,sana,sangat,sangatlah,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,sekarang,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,tadi,tadinya,tahu,tahun,tak,tambah,tambahnya,tampak,tampaknya,tandas,tandasnya,tanpa,tanya,tanyakan,tanyanya,tapi,tegas,tegasnya,telah,tempat,tengah,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,tinggi,toh,tunjuk,turut,tutur,tuturnya,ucap,ucapnya,ujar,ujarnya,umum,umumnya,ungkap,ungkapnya,untuk,usah,usai,waduh,wah,wahai,waktu,waktunya,walau,walaupun,wong,yaitu,yakin,yakni,yang

data/lib/stopwords/snowball/locales/ko.csv

@@ -0,0 +1 @@
+0,1,2,3,4,5,6,7,8,9,０,１,２,３,４,５,６,７,８,９,가,가까스로,가령,각,각각,각자,각종,갖고말하자면,같다,같이,개의치않고,거니와,거바,거의,것,것과 같이,것들,게다가,게우다,겨우,견지에서,결과에 이르다,결국,결론을 낼 수 있다,겸사겸사,고려하면,고로,곧,공동으로,과,과연,관계가 있다,관계없이,관련이 있다,관하여,관한,관해서는,구,구체적으로,구토하다,그,그들,그때,그래,그래도,그래서,그러나,그러니,그러니까,그러면,그러므로,그러한즉,그런 까닭에,그런데,그런즉,그럼,그럼에도 불구하고,그렇게 함으로써,그렇지,그렇지 않다면,그렇지 않으면,그렇지만,그렇지않으면,그리고,그리하여,그만이다,그에 따르는,그위에,그저,그중에서,그치지 않다,근거로,근거하여,기대여,기점으로,기준으로,기타,까닭으로,까악,까지,까지 미치다,까지도,꽈당,끙끙,끼익,나,나머지는,남들,남짓,너,너희,너희들,네,넷,년,논하지 않다,놀라다,누가 알겠는가,누구,다른,다른 방면으로,다만,다섯,다소,다수,다시 말하자면,다시말하면,다음,다음에,다음으로,단지,답다,당신,당장,대로 하다,대하면,대하여,대해 말하자면,대해서,댕그,더구나,더군다나,더라도,더불어,더욱더,더욱이는,도달하다,도착하다,동시에,동안,된바에야,된이상,두번째로,둘,둥둥,뒤따라,뒤이어,든간에,들,등,등등,딩동,따라,따라서,따위,따지지 않다,딱,때,때가 되어,때문에,또,또한,뚝뚝,라 해도,령,로,로 인하여,로부터,로써,륙,를,마음대로,마저,마저도,마치,막론하고,만 못하다,만약,만약에,만은 아니다,만이 아니다,만일,만큼,말하자면,말할것도 없고,매,매번,메쓰겁다,몇,모,모두,무렵,무릎쓰고,무슨,무엇,무엇때문에,물론,및,바꾸어말하면,바꾸어말하자면,바꾸어서 말하면,바꾸어서 한다면,바꿔 말하면,바로,바와같이,밖에 안된다,반대로,반대로 말하자면,반드시,버금,보는데서,보다더,보드득,본대로,봐,봐라,부류의 사람들,부터,불구하고,불문하고,붕붕,비걱거리다,비교적,비길수 없다,비로소,비록,비슷하다,비추어 보아,비하면,뿐만 아니라,뿐만아니라,뿐이다,삐걱,삐걱거리다,사,삼,상대적으로 말하자면,생각한대로,설령,설마,설사,셋,소생,소인,솨,쉿,습니까,습니다,시각,시간,시작하여,시초에,시키다,실로,심지어,아,아니,아니나다를가,아니라면,아니면,아니었다면,아래윗,아무거나,아무도,아야,아울러,아이,아이고,아이구,아이야,아이쿠,아하,아홉,안 그러면,않기 위하여,않기 위해서,알 수 있다,알았어,앗,앞에서,앞의것,야,약간,양자,어,어기여차,어느,어느 년도,어느것,어느곳,어느때,어느쪽,어느해,어디,어때,어떠한,어떤,어떤것,어떤것들,어떻게,어떻해,어이,어째서,어쨋든,어쩔수 없다,어찌,어찌됏든,어찌됏어,어찌하든지,어찌하여,언제,언젠가,얼마,얼마 안 되는 것,얼마간,얼마나,얼마든지,얼마만큼,얼마큼,엉엉,에,에 가서,에 달려 있다,에 대해,에 있다,에 한하다,에게,에서,여,여기,여덟,여러분,여보시오,여부,여섯,여전히,여차,연관되다,연이서,영,영차,옆사람,예,예를 들면,예를 들자면,예컨대,예하면,오,오로지,오르다,오자마자,오직,오호,오히려,와,와 같은 사람들,와르르,와아,왜,왜냐하면,외에도,요만큼,요만한 것,요만한걸,요컨대,우르르,우리,우리들,우선,우에 종합한것과같이,운운,월,위에서 서술한바와같이,위하여,위해서,윙윙,육,으로,으로 인하여,으로서,으로써,을,응,응당,의,의거하여,의지하여,의해,의해되다,의해서,이,이 되다,이 때문에,이 밖에,이 외에,이 정도의,이것,이곳,이때,이라면,이래,이러이러하다,이러한,이런,이럴정도로,이렇게 많은 것,이렇게되면,이렇게말하자면,이렇구나,이로 인하여,이르기까지,이리하여,이만큼,이번,이봐,이상,이어서,이었다,이와 같다,이와 같은,이와 반대로,이와같다면,이외에도,이용하여,이유만으로,이젠,이지만,이쪽,이천구,이천육,이천칠,이천팔,인 듯하다,인젠,일,일것이다,일곱,일단,일때,일반적으로,일지라도,임에 틀림없다,입각하여,입장에서,잇따라,있다,자,자기,자기집,자마자,자신,잠깐,잠시,저,저것,저것만큼,저기,저쪽,저희,전부,전자,전후,점에서 보아,정도에 이르다,제,제각기,제외하고,조금,조차,조차도,졸졸,좀,좋아,좍좍,주룩주룩,주저하지 않고,줄은 몰랏다,줄은모른다,중에서,중의하나,즈음하여,즉,즉시,지든지,지만,지말고,진짜로,쪽으로,차라리,참,참나,첫번째로,쳇,총적으로,총적으로 말하면,총적으로 보면,칠,콸콸,쾅쾅,쿵,타다,타인,탕탕,토하다,통하여,툭,퉤,틈타,팍,팔,퍽,펄렁,하,하게될것이다,하게하다,하겠는가,하고 있다,하고있었다,하곤하였다,하구나,하기 때문에,하기 위하여,하기는한데,하기만 하면,하기보다는,하기에,하나,하느니,하는 김에,하는 편이 낫다,하는것도,하는것만 못하다,하는것이 낫다,하는바,하더라도,하도다,하도록시키다,하도록하다,하든지,하려고하다,하마터면,하면 할수록,하면된다,하면서,하물며,하여금,하여야,하자마자,하지 않는다면,하지 않도록,하지마,하지마라,하지만,하하,한 까닭에,한 이유는,한 후,한다면,한다면 몰라도,한데,한마디,한적이있다,한켠으로는,한항목,할 따름이다,할 생각이다,할 줄 안다,할 지경이다,할 힘이 있다,할때,할만하다,할망정,할뿐,할수있다,할수있어,할줄알다,할지라도,할지언정,함께,해도된다,해도좋다,해봐요,해서는 안된다,해야한다,해요,했어요,향하다,향하여,향해서,허,허걱,허허,헉,헉헉,헐떡헐떡,형식으로 쓰여,혹시,혹은,혼자,훨씬,휘익,휴,흐흐,흥,힘입어,︿,～,￥

data/lib/stopwords/snowball/locales/pl.csv

@@ -0,0 +1 @@
+a,aby,ach,acz,aczkolwiek,aj,albo,ale,ależ,ani,aż,bardziej,bardzo,bo,bowiem,by,byli,bynajmniej,być,był,była,było,były,będzie,będą,cali,cała,cały,ci,cię,ciebie,co,cokolwiek,coś,czasami,czasem,czemu,czy,czyli,daleko,dla,dlaczego,dlatego,do,dobrze,dokąd,dość,dużo,dwa,dwaj,dwie,dwoje,dziś,dzisiaj,gdy,gdyby,gdyż,gdzie,gdziekolwiek,gdzieś,i,ich,ile,im,inna,inne,inny,innych,iż,ja,ją,jak,jakaś,jakby,jaki,jakichś,jakie,jakiś,jakiż,jakkolwiek,jako,jakoś,je,jeden,jedna,jedno,jednak,jednakże,jego,jej,jemu,jest,jestem,jeszcze,jeśli,jeżeli,już,ją,każdy,kiedy,kilka,kimś,kto,ktokolwiek,ktoś,która,które,którego,której,który,których,którym,którzy,ku,lat,lecz,lub,ma,mają,mało,mam,mi,mimo,między,mną,mnie,mogą,moi,moim,moja,moje,może,możliwe,można,mój,mu,musi,my,na,nad,nam,nami,nas,nasi,nasz,nasza,nasze,naszego,naszych,natomiast,natychmiast,nawet,nią,nic,nich,nie,niech,niego,niej,niemu,nigdy,nim,nimi,niż,no,o,obok,od,około,on,ona,one,oni,ono,oraz,oto,owszem,pan,pana,pani,po,pod,podczas,pomimo,ponad,ponieważ,powinien,powinna,powinni,powinno,poza,prawie,przecież,przed,przede,przedtem,przez,przy,roku,również,sama,są,się,skąd,sobie,sobą,sposób,swoje,ta,tak,taka,taki,takie,także,tam,te,tego,tej,temu,ten,teraz,też,to,tobą,tobie,toteż,trzeba,tu,tutaj,twoi,twoim,twoja,twoje,twym,twój,ty,tych,tylko,tym,u,w,wam,wami,was,wasz,wasza,wasze,we,według,wiele,wielu,więc,więcej,wszyscy,wszystkich,wszystkie,wszystkim,wszystko,wtedy,wy,właśnie,z,za,zapewne,zawsze,ze,zł,znowu,znów,został,żaden,żadna,żadne,żadnych,że,żeby

data/lib/stopwords/snowball/locales/ro.csv

@@ -0,0 +1 @@
+acea,aceasta,această,aceea,acei,aceia,acel,acela,acele,acelea,acest,acesta,aceste,acestea,aceşti,aceştia,acolo,acord,acum,ai,aia,aibă,aici,al,ăla,ale,alea,ălea,altceva,altcineva,am,ar,are,aş,aşadar,asemenea,asta,ăsta,astăzi,astea,ăstea,ăştia,asupra,aţi,au,avea,avem,aveţi,azi,bine,bucur,bună,ca,că,căci,când,care,cărei,căror,cărui,cât,câte,câţi,către,câtva,caut,ce,cel,ceva,chiar,cinci,cînd,cine,cineva,cît,cîte,cîţi,cîtva,contra,cu,cum,cumva,curând,curînd,da,dă,dacă,dar,dată,datorită,dau,de,deci,deja,deoarece,departe,deşi,din,dinaintea,dintr-,dintre,doi,doilea,două,drept,după,ea,ei,el,ele,eram,este,eşti,eu,face,fără,fata,fi,fie,fiecare,fii,fim,fiţi,fiu,frumos,graţie,halbă,iar,ieri,îi,îl,îmi,împotriva,în ,înainte,înaintea,încât,încît,încotro,între,întrucât,întrucît,îţi,la,lângă,le,li,lîngă,lor,lui,mă,mai,mâine,mea,mei,mele,mereu,meu,mi,mie,mîine,mine,mult,multă,mulţi,mulţumesc,ne,nevoie,nicăieri,nici,nimeni,nimeri,nimic,nişte,noastră,noastre,noi,noroc,noştri,nostru,nouă,nu,opt,ori,oricând,oricare,oricât,orice,oricînd,oricine,oricît,oricum,oriunde,până,patra,patru,patrulea,pe,pentru,peste,pic,pînă,poate,pot,prea,prima,primul,prin,puţin,puţina,puţină,rog,sa,să,săi,sale,şapte,şase,sau,său,se,şi,sînt,sîntem,sînteţi,spate,spre,ştiu,sub,sunt,suntem,sunteţi,sută,ta,tăi,tale,tău,te,ţi,ţie,timp,tine,toată,toate,tot,toţi,totuşi,trei,treia,treilea,tu,un,una,unde,undeva,unei,uneia,unele,uneori,unii,unor,unora,unu,unui,unuia,unul,vă,vi,voastră,voastre,voi,voştri,vostru,vouă,vreme,vreo,vreun,zece,zero,zi,zice

data/lib/stopwords/snowball/locales/ru.csv

@@ -1,159 +1 @@
-É
-×
-×Ï
-ÎÅ
-ÞÔÏ
-ÏÎ
-ÎÁ
-Ñ
-Ó
-ÓÏ
-ËÁË
-Á
-ÔÏ
-×ÓÅ
-ÏÎÁ
-ÔÁË
-ÅÇÏ
-ÎÏ
-ÄÁ
-ÔÙ
-Ë
-Õ
-ÖÅ
-×Ù
-ÚÁ
-ÂÙ
-ÐÏ
-ÔÏÌØËÏ
-ÅÅ
-ÍÎÅ
-ÂÙÌÏ
-×ÏÔ
-ÏÔ
-ÍÅÎÑ
-ÅÝÅ
-ÎÅÔ
-Ï
-ÉÚ
-ÅÍÕ
-ÔÅÐÅÒØ
-ËÏÇÄÁ
-ÄÁÖÅ
-ÎÕ
-×ÄÒÕÇ
-ÌÉ
-ÅÓÌÉ
-ÕÖÅ
-ÉÌÉ
-ÎÉ
-ÂÙÔØ
-ÂÙÌ
-ÎÅÇÏ
-ÄÏ
-×ÁÓ
-ÎÉÂÕÄØ
-ÏÐÑÔØ
-ÕÖ
-×ÁÍ
-ÓËÁÚÁÌ
-×ÅÄØ
-ÔÁÍ
-ÐÏÔÏÍ
-ÓÅÂÑ
-ÎÉÞÅÇÏ
-ÅÊ
-ÍÏÖÅÔ
-ÏÎÉ
-ÔÕÔ
-ÇÄÅ
-ÅÓÔØ
-ÎÁÄÏ
-ÎÅÊ
-ÄÌÑ
-ÍÙ
-ÔÅÂÑ
-ÉÈ
-ÞÅÍ
-ÂÙÌÁ
-ÓÁÍ
-ÞÔÏÂ
-ÂÅÚ
-ÂÕÄÔÏ
-ÞÅÌÏ×ÅË
-ÞÅÇÏ
-ÒÁÚ
-ÔÏÖÅ
-ÓÅÂÅ
-ÐÏÄ
-ÖÉÚÎØ
-ÂÕÄÅÔ
-Ö
-ÔÏÇÄÁ
-ËÔÏ
-ÜÔÏÔ
-ÇÏ×ÏÒÉÌ
-ÔÏÇÏ
-ÐÏÔÏÍÕ
-ÜÔÏÇÏ
-ËÁËÏÊ
-ÓÏ×ÓÅÍ
-ÎÉÍ
-ÚÄÅÓØ
-ÜÔÏÍ
-ÏÄÉÎ
-ÐÏÞÔÉ
-ÍÏÊ
-ÔÅÍ
-ÞÔÏÂÙ
-ÎÅÅ
-ËÁÖÅÔÓÑ
-ÓÅÊÞÁÓ
-ÂÙÌÉ
-ËÕÄÁ
-ÚÁÞÅÍ
-ÓËÁÚÁÔØ
-×ÓÅÈ
-ÎÉËÏÇÄÁ
-ÓÅÇÏÄÎÑ
-ÍÏÖÎÏ
-ÐÒÉ
-ÎÁËÏÎÅÃ
-Ä×Á
-ÏÂ
-ÄÒÕÇÏÊ
-ÈÏÔØ
-ÐÏÓÌÅ
-ÎÁÄ
-ÂÏÌØÛÅ
-ÔÏÔ
-ÞÅÒÅÚ
-ÜÔÉ
-ÎÁÓ
-ÐÒÏ
-×ÓÅÇÏ
-ÎÉÈ
-ËÁËÁÑ
-ÍÎÏÇÏ
-ÒÁÚ×Å
-ÓËÁÚÁÌÁ
-ÔÒÉ
-ÜÔÕ
-ÍÏÑ
-×ÐÒÏÞÅÍ
-ÈÏÒÏÛÏ
-Ó×ÏÀ
-ÜÔÏÊ
-ÐÅÒÅÄ
-ÉÎÏÇÄÁ
-ÌÕÞÛÅ
-ÞÕÔØ
-ÔÏÍ
-ÎÅÌØÚÑ
-ÔÁËÏÊ
-ÉÍ
-ÂÏÌÅÅ
-×ÓÅÇÄÁ
-ËÏÎÅÞÎÏ
-×ÓÀ
-ÍÅÖÄÕ
+и,в,во,не,что,он,на,я,с,со,как,а,то,все,она,так,его,но,да,ты,к,у,же,вы,за,бы,по,только,ее,мне,было,вот,от,меня,еще,нет,о,из,ему,теперь,когда,даже,ну,вдруг,ли,если,уже,или,ни,быть,был,него,до,вас,нибудь,опять,уж,вам,сказал,ведь,там,потом,себя,ничего,ей,может,они,тут,где,есть,надо,ней,для,мы,тебя,их,чем,была,сам,чтоб,без,будто,человек,чего,раз,тоже,себе,под,жизнь,будет,ж,тогда,кто,этот,говорил,того,потому,этого,какой,совсем,ним,здесь,этом,один,почти,мой,тем,чтобы,нее,кажется,сейчас,были,куда,зачем,сказать,всех,никогда,сегодня,можно,при,наконец,два,об,другой,хоть,после,над,больше,тот,через,эти,нас,про,всего,них,какая,много,разве,сказала,три,эту,моя,впрочем,хорошо,свою,этой,перед,иногда,лучше,чуть,том,нельзя,такой,им,более,всегда,конечно,всю,между

data/lib/stopwords/snowball/locales/sv.csv

@@ -1,114 +1 @@
-och
-det
-att
-i
-en
-jag
-hon
-som
-han
-på
-den
-med
-var
-sig
-för
-så
-till
-är
-men
-ett
-om
-hade
-de
-av
-icke
-mig
-du
-henne
-då
-sin
-nu
-har
-inte
-hans
-honom
-skulle
-hennes
-där
-min
-man
-ej
-vid
-kunde
-något
-från
-ut
-när
-efter
-upp
-vi
-dem
-vara
-vad
-över
-än
-dig
-kan
-sina
-här
-ha
-mot
-alla
-under
-någon
-eller
-allt
-mycket
-sedan
-ju
-denna
-själv
-detta
-åt
-utan
-varit
-hur
-ingen
-mitt
-ni
-bli
-blev
-oss
-din
-dessa
-några
-deras
-blir
-mina
-samma
-vilken
-er
-sådan
-vår
-blivit
-dess
-inom
-mellan
-sådant
-varför
-varje
-vilka
-ditt
-vem
-vilket
-sitta
-sådana
-vart
-dina
-vars
-vårt
-våra
-ert
-era
-vilkas
+och,det,att,i,en,jag,hon,som,han,på,den,med,var,sig,för,så,till,är,men,ett,om,hade,de,av,icke,mig,du,henne,då,sin,nu,har,inte,hans,honom,skulle,hennes,där,min,man,ej,vid,kunde,något,från,ut,när,efter,upp,vi,dem,vara,vad,över,än,dig,kan,sina,här,ha,mot,alla,under,någon,eller,allt,mycket,sedan,ju,denna,själv,detta,åt,utan,varit,hur,ingen,mitt,ni,bli,blev,oss,din,dessa,några,deras,blir,mina,samma,vilken,er,sådan,vår,blivit,dess,inom,mellan,sådant,varför,varje,vilka,ditt,vem,vilket,sitta,sådana,vart,dina,vars,vårt,våra,ert,era,vilkas

data/lib/stopwords/snowball/locales/th.csv

@@ -0,0 +1 @@
+กล่าว,กว่า,กัน,กับ,การ,ก็,ก่อน,ขณะ,ขอ,ของ,ขึ้น,คง,ครั้ง,ความ,คือ,จะ,จัด,จาก,จึง,ช่วง,ซึ่ง,ดัง,ด้วย,ด้าน,ตั้ง,ตั้งแต่,ตาม,ต่อ,ต่าง,ต่างๆ,ต้อง,ถึง,ถูก,ถ้า,ทั้ง,ทั้งนี้,ทาง,ที่,ที่สุด,ทุก,ทํา,ทําให้,นอกจาก,นัก,นั้น,นี้,น่า,นํา,บาง,ผล,ผ่าน,พบ,พร้อม,มา,มาก,มี,ยัง,รวม,ระหว่าง,รับ,ราย,ร่วม,ลง,วัน,ว่า,สุด,ส่ง,ส่วน,สําหรับ,หนึ่ง,หรือ,หลัง,หลังจาก,หลาย,หาก,อยาก,อยู่,อย่าง,ออก,อะไร,อาจ,อีก,เขา,เข้า,เคย,เฉพาะ,เช่น,เดียว,เดียวกัน,เนื่องจาก,เปิด,เปิดเผย,เป็น,เป็นการ,เพราะ,เพื่อ,เมื่อ,เรา,เริ่ม,เลย,เห็น,เอง,แต่,แบบ,แรก,และ,แล้ว,แห่ง,โดย,ใน,ให้,ได้,ไป,ไม่,ไว้

data/lib/stopwords/snowball/locales/tr.csv

@@ -0,0 +1 @@
+acaba,acep,adeta,altmış,altmış,altı,altı,ama,ancak,arada,artık,aslında,aynen,ayrıca,az,bana,bari,bazen,bazı,bazı,başka,belki,ben,benden,beni,benim,beri,beş,beş,beş,bile,bin,bir,biraz,biri,birkaç,birkez,birçok,birşey,birşeyi,birşey,birşeyi,birşey,biz,bizden,bize,bizi,bizim,bu,buna,bunda,bundan,bunlar,bunları,bunların,bunu,bunun,burada,böyle,böylece,bütün,da,daha,dahi,dahil,daima,dair,dayanarak,de,defa,deđil,değil,diye,diđer,diğer,doksan,dokuz,dolayı,dolayısıyla,dört,edecek,eden,ederek,edilecek,ediliyor,edilmesi,ediyor,elli,en,etmesi,etti,ettiği,ettiğini,eđer,eğer,fakat,gibi,göre,halbuki,halen,hangi,hani,hariç,hatta,hele,hem,henüz,hep,hepsi,her,herhangi,herkes,herkesin,hiç,hiçbir,iken,iki,ila,ile,ilgili,ilk,illa,ise,itibaren,itibariyle,iyi,iyice,için,işte,işte,kadar,kanımca,karşın,katrilyon,kendi,kendilerine,kendini,kendisi,kendisine,kendisini,kere,kez,keşke,ki,kim,kimden,kime,kimi,kimse,kırk,kısaca,kırk,lakin,madem,međer,milyar,milyon,mu,mü,mı,mı,nasıl,nasıl,ne,neden,nedenle,nerde,nere,nerede,nereye,nitekim,niye,niçin,o,olan,olarak,oldu,olduklarını,olduğu,olduğunu,olmadı,olmadığı,olmak,olması,olmayan,olmaz,olsa,olsun,olup,olur,olursa,oluyor,on,ona,ondan,onlar,onlardan,onlari,onların,onları,onların,onu,onun,otuz,oysa,pek,rağmen,sadece,sanki,sekiz,seksen,sen,senden,seni,senin,siz,sizden,sizi,sizin,sonra,tarafından,trilyon,tüm,var,vardı,ve,veya,veyahut,ya,yahut,yani,yapacak,yapmak,yaptı,yaptıkları,yaptığı,yaptığını,yapılan,yapılması,yapıyor,yedi,yerine,yetmiş,yetmiş,yetmiş,yine,yirmi,yoksa,yüz,zaten,çok,çünkü,öyle,üzere,üç,şey,şeyden,şeyi,şeyler,şu,şuna,şunda,şundan,şunu,şey,şeyden,şeyi,şeyler,şu,şuna,şunda,şundan,şunları,şunu,şöyle,şayet,şimdi,şu,şöyle

data/lib/stopwords/snowball/locales/vi.csv

@@ -0,0 +1 @@
+bị,bởi,cả,các,cái,cần,càng,chỉ,chiếc,cho,chứ,chưa,chuyện,có,có thể,cứ,của,cùng,cũng,đã,đang,để,đến nỗi,đều,điều,do,đó,được,dưới,gì,khi,không,là,lại,lên,lúc,mà,mỗi,một cách,này,nên,nếu,ngay,nhiều,như,nhưng,những,nơi,nữa,phải,qua,ra,rằng,rất,rồi,sau,sẽ,so,sự,tại,theo,thì,trên,trước,từ,từng,và,vẫn,vào,vậy,vì,việc,với,vừa,vâng,à,ừ,từ

data/spec/lib/filter_spec.rb

@@ -5,13 +5,14 @@ describe Stopwords::Filter do
   context "when fed with a list of arbitrary words" do
 
     let (:filter) { Stopwords::Filter.new stopwords }
-    let (:stopwords) { ["a", "desde"] }
+    let (:stopwords) { ["A", "desde"] }
 
     subject { filter }
 
-    it("should remove the stopwords for the list of words to be filtered") { filter.filter("desde Santurce a Bilbao".split).should == ["Santurce", "Bilbao"]}
+    it("should remove the stopwords for the list of words to be filtered") { expect(filter.filter("desde Santurce A Bilbao".split)).to eq ["Santurce", "Bilbao"]}
+    it("should remove stopwords even if upcase and downcases doesn't match") { expect(filter.filter("Desde Santurce a Bilbao".split)).to eq ["Santurce", "Bilbao"]}
 
   end
 
 
-end
+end

data/spec/lib/snowball_filter_spec.rb

@@ -9,9 +9,9 @@ describe Stopwords::Snowball::Filter do
 
     subject { filter }
 
-    its(:stopwords) { should == ["de", "la", "que", "el", "en", "y", "a", "los", "del", "se", "las", "por", "un", "para", "con", "no", "una", "su", "al", "lo", "como", "más", "pero", "sus", "le", "ya", "o", "este", "sí", "porque", "esta", "entre", "cuando", "muy", "sin", "sobre", "también", "me", "hasta", "hay", "donde", "quien", "desde", "todo", "nos", "durante", "todos", "uno", "les", "ni", "contra", "otros", "ese", "eso", "ante", "ellos", "e", "esto", "mí", "antes", "algunos", "qué", "unos", "yo", "otro", "otras", "otra", "él", "tanto", "esa", "estos", "mucho", "quienes", "nada", "muchos", "cual", "poco", "ella", "estar", "estas", "algunas", "algo", "nosotros", "mi", "mis", "tú", "te", "ti", "tu", "tus", "ellas", "nosotras", "vosotros", "vosotras", "os", "mío", "mía", "míos", "mías", "tuyo", "tuya", "tuyos", "tuyas", "suyo", "suya", "suyos", "suyas", "nuestro", "nuestra", "nuestros", "nuestras", "vuestro", "vuestra", "vuestros", "vuestras", "esos", "esas", "estoy", "estás", "está", "estamos", "estáis", "están", "esté", "estés", "estemos", "estéis", "estén", "estaré", "estarás", "estará", "estaremos", "estaréis", "estarán", "estaría", "estarías", "estaríamos", "estaríais", "estarían", "estaba", "estabas", "estábamos", "estabais", "estaban", "estuve", "estuviste", "estuvo", "estuvimos", "estuvisteis", "estuvieron", "estuviera", "estuvieras", "estuviéramos", "estuvierais", "estuvieran", "estuviese", "estuvieses", "estuviésemos", "estuvieseis", "estuviesen", "estando", "estado", "estada", "estados", "estadas", "estad", "he", "has", "ha", "hemos", "habéis", "han", "haya", "hayas", "hayamos", "hayáis", "hayan", "habré", "habrás", "habrá", "habremos", "habréis", "habrán", "habría", "habrías", "habríamos", "habríais", "habrían", "había", "habías", "habíamos", "habíais", "habían", "hube", "hubiste", "hubo", "hubimos", "hubisteis", "hubieron", "hubiera", "hubieras", "hubiéramos", "hubierais", "hubieran", "hubiese", "hubieses", "hubiésemos", "hubieseis", "hubiesen", "habiendo", "habido", "habida", "habidos", "habidas", "soy", "eres", "es", "somos", "sois", "son", "sea", "seas", "seamos", "seáis", "sean", "seré", "serás", "será", "seremos", "seréis", "serán", "sería", "serías", "seríamos", "seríais", "serían", "era", "eras", "éramos", "erais", "eran", "fui", "fuiste", "fue", "fuimos", "fuisteis", "fueron", "fuera", "fueras", "fuéramos", "fuerais", "fueran", "fuese", "fueses", "fuésemos", "fueseis", "fuesen", "siendo", "sido", "tengo", "tienes", "tiene", "tenemos", "tenéis", "tienen", "tenga", "tengas", "tengamos", "tengáis", "tengan", "tendré", "tendrás", "tendrá", "tendremos", "tendréis", "tendrán", "tendría", "tendrías", "tendríamos", "tendríais", "tendrían", "tenía", "tenías", "teníamos", "teníais", "tenían", "tuve", "tuviste", "tuvo", "tuvimos", "tuvisteis", "tuvieron", "tuviera", "tuvieras", "tuviéramos", "tuvierais", "tuvieran", "tuviese", "tuvieses", "tuviésemos", "tuvieseis", "tuviesen", "teniendo", "tenido", "tenida", "tenidos", "tenidas", "tened"]}
+    it("should have the appropiate stopwords") { expect(subject.stopwords).to eq ["de","la","que","el","en","y","a","los","del","se","las","por","un","para","con","no","una","su","al","lo","como","más","pero","sus","le","ya","o","este","sí","porque","esta","entre","cuando","muy","sin","sobre","también","me","hasta","hay","donde","quien","desde","todo","nos","durante","todos","uno","les","ni","contra","otros","ese","eso","ante","ellos","e","esto","mí","antes","algunos","qué","unos","yo","otro","otras","otra","él","tanto","esa","estos","mucho","quienes","nada","muchos","cual","poco","ella","estar","estas","algunas","algo","nosotros","mi","mis","tú","te","ti","tu","tus","ellas","nosotras","vosotros","vosotras","os","mío","mía","míos","mías","tuyo","tuya","tuyos","tuyas","suyo","suya","suyos","suyas","nuestro","nuestra","nuestros","nuestras","vuestro","vuestra","vuestros","vuestras","esos","esas","estoy","estás","está","estamos","estáis","están","esté","estés","estemos","estéis","estén","estaré","estarás","estará","estaremos","estaréis","estarán","estaría","estarías","estaríamos","estaríais","estarían","estaba","estabas","estábamos","estabais","estaban","estuve","estuviste","estuvo","estuvimos","estuvisteis","estuvieron","estuviera","estuvieras","estuviéramos","estuvierais","estuvieran","estuviese","estuvieses","estuviésemos","estuvieseis","estuviesen","estando","estada","estadas","estad","he","has","ha","hemos","habéis","han","haya","hayas","hayamos","hayáis","hayan","habré","habrás","habrá","habremos","habréis","habrán","habría","habrías","habríamos","habríais","habrían","había","habías","habíamos","habíais","habían","hube","hubiste","hubo","hubimos","hubisteis","hubieron","hubiera","hubieras","hubiéramos","hubierais","hubieran","hubiese","hubieses","hubiésemos","hubieseis","hubiesen","habiendo","habido","habida","habidos","habidas","soy","eres","es","somos","sois","son","sea","seas","seamos","seáis","sean","seré","serás","será","seremos","seréis","serán","sería","serías","seríamos","seríais","serían","era","eras","éramos","erais","eran","fui","fuiste","fue","fuimos","fuisteis","fueron","fuera","fueras","fuéramos","fuerais","fueran","fuese","fueses","fuésemos","fueseis","fuesen","siendo","sido","tengo","tienes","tiene","tenemos","tenéis","tienen","tenga","tengas","tengamos","tengáis","tengan","tendré","tendrás","tendrá","tendremos","tendréis","tendrán","tendría","tendrías","tendríamos","tendríais","tendrían","tenía","tenías","teníamos","teníais","tenían","tuve","tuviste","tuvo","tuvimos","tuvisteis","tuvieron","tuviera","tuvieras","tuviéramos","tuvierais","tuvieran","tuviese","tuvieses","tuviésemos","tuvieseis","tuviesen","teniendo","tenido","tenida","tenidos","tenidas","tened","algunes","algunxs","elle","ellx","elles","ellxs","ese","esx","eses","esxs","estes","este","estxs","estx","lx","le","lxs","les","mucha","muchas","muches","muchxs","míe","míes","míx","míxs","nosotres","nosotrxs","nuestre","nuestres","nuestrx","nuestrxs","otre","otrx","otres","otrxs","poca","poque","pocx","suye","suyx","suyes","suyxs","tantas","tantxs","tantes","tenide","tenides","tenidx","tenidxs","toda","todas","tode","todes","todx","todxs","tuye","tuyes","tuyx","tuyxs","une","unx","unxs","unes","vosotrxs","vosotres","vuestre","vuestres","vuestrx","vuestrxs"]}
 
-    it("should remove the stopwords for the list of words to be filtered") { filter.filter("desde Santurce a Bilbao".split).should == ["Santurce", "Bilbao"]}
+    it("should remove the stopwords for the list of words to be filtered") { expect(filter.filter("desde Santurce a Bilbao".split)).to eq ["Santurce", "Bilbao"]}
 
   end
 
@@ -21,7 +21,17 @@ describe Stopwords::Snowball::Filter do
 
     subject { filter }
 
-    it("should remove the stopwords for the list of words to be filtered") { filter.filter("desde Santurce a Bilbao".split).should == ["Bilbao"]}
+    it("should remove the stopwords for the list of words to be filtered") { expect(filter.filter("desde Santurce a Bilbao".split)).to eq ["Bilbao"]}
+
+  end
+
+  context "when locale is not found" do
+
+    let (:filter) { Stopwords::Snowball::Filter.new "no-real" }
+
+    subject { filter }
+
+    it("should throw an error explaining the locale not found") { expect{filter}.to raise_error(ArgumentError)}
 
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: stopwords-filter
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.6.0
 platform: ruby
 authors:
 - David J. Brenes
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-08-03 00:00:00.000000000 Z
+date: 2021-10-21 00:00:00.000000000 Z
 dependencies: []
 description: Small library that allows you to create a simple stopwords filter or
   use some based on Snowball stopwords lists
@@ -30,19 +30,35 @@ files:
 - lib/stopwords/filter.rb
 - lib/stopwords/snowball.rb
 - lib/stopwords/snowball/filter.rb
+- lib/stopwords/snowball/locales/af.csv
+- lib/stopwords/snowball/locales/ar.csv
 - lib/stopwords/snowball/locales/bg.csv
+- lib/stopwords/snowball/locales/bn.csv
+- lib/stopwords/snowball/locales/br.csv
+- lib/stopwords/snowball/locales/ca.csv
+- lib/stopwords/snowball/locales/cs.csv
 - lib/stopwords/snowball/locales/da.csv
 - lib/stopwords/snowball/locales/de.csv
+- lib/stopwords/snowball/locales/el.csv
 - lib/stopwords/snowball/locales/en.csv
 - lib/stopwords/snowball/locales/es.csv
+- lib/stopwords/snowball/locales/fi.csv
 - lib/stopwords/snowball/locales/fn.csv
 - lib/stopwords/snowball/locales/fr.csv
+- lib/stopwords/snowball/locales/he.csv
 - lib/stopwords/snowball/locales/hu.csv
+- lib/stopwords/snowball/locales/id.csv
 - lib/stopwords/snowball/locales/it.csv
+- lib/stopwords/snowball/locales/ko.csv
 - lib/stopwords/snowball/locales/nl.csv
+- lib/stopwords/snowball/locales/pl.csv
 - lib/stopwords/snowball/locales/pt.csv
+- lib/stopwords/snowball/locales/ro.csv
 - lib/stopwords/snowball/locales/ru.csv
 - lib/stopwords/snowball/locales/sv.csv
+- lib/stopwords/snowball/locales/th.csv
+- lib/stopwords/snowball/locales/tr.csv
+- lib/stopwords/snowball/locales/vi.csv
 - lib/stopwords/snowball/wordsieve.rb
 - spec/lib/filter_spec.rb
 - spec/lib/snowball_filter_spec.rb
@@ -57,17 +73,17 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.2
+rubygems_version: 2.6.14.1
 signing_key: 
 specification_version: 4
 summary: Snowball based filters for stopwords

data/lib/stopwords/snowball/locales/fn.csv

@@ -1 +0,0 @@
-olla,olen,olet,on,olemme,olette,ovat,ole,oli,olisi,olisit,olisin,olisimme,olisitte,olisivat,olit,olin,olimme,olitte,olivat,ollut,olleet,en,et,ei,emme,ette,eivät,minä,minun,minut,minua,minussa,minusta,minuun,minulla,minulta,minulle,sinä,sinun,sinut,sinua,sinussa,sinusta,sinuun,sinulla,sinulta,sinulle,hän,hänen,hänet,häntä,hänessä,hänestä,häneen,hänellä,häneltä,hänelle,me,meidän,meidät,meitä,meissä,meistä,meihin,meillä,meiltä,meille,te,teidän,teidät,teitä,teissä,teistä,teihin,teillä,teiltä,teille,he,heidän,heidät,heitä,heissä,heistä,heihin,heillä,heiltä,heille,tämä,tämän,tätä,tässä,tästä,tähän,tällä,tältä,tälle,tänä,täksi,tuo,tuon,tuota,tuossa,tuosta,tuohon,tuolla,tuolta,tuolle,tuona,tuoksi,se,sen,sitä,siinä,siitä,siihen,sillä,siltä,sille,sinä,siksi,nämä,näiden,näitä,näissä,näistä,näihin,näillä,näiltä,näille,näinä,näiksi,nuo,noiden,noita,noissa,noista,noihin,noilla,noilta,noille,noina,noiksi,ne,niiden,niitä,niissä,niistä,niihin,niillä,niiltä,niille,niinä,niiksi,kuka,kenen,kenet,ketä,kenessä,kenestä,keneen,kenellä,keneltä,kenelle,kenenä,keneksi,ketkä,keiden,ketkä,keitä,keissä,keistä,keihin,keillä,keiltä,keille,keinä,keiksi,mikä,minkä,minkä,mitä,missä,mistä,mihin,millä,miltä,mille,minä,miksi,mitkä,joka,jonka,jota,jossa,josta,johon,jolla,jolta,jolle,jona,joksi,jotka,joiden,joita,joissa,joista,joihin,joilla,joilta,joille,joina,joiksi,että,ja,jos,koska,kuin,mutta,niin,sekä,sillä,tai,vaan,vai,vaikka,kanssa,mukaan,noin,poikki,yli,kun,niin,nyt,itse