stopwords-filter 0.1.0 → 0.2.0

data/CHANGELOG

@@ -0,0 +1,7 @@
+0.2.0:
+ * Added stopword? method [@s2gatev]
+ * Added Sieve class [@s2gatev]
+ * Added bulgarian language [@s2gatev]
+0.1.0
+ * Added simple filter [@brenes]
+ * Added snowball filter [@brenes]

data/README.md

@@ -29,7 +29,12 @@ in your Gemfile.
 ```
 stopwords = ['by', 'written', 'from']
 filter = Stopwords::Filter.new stopwords
-filter.filter 'guide by douglas adams'.split #-> ['guide', 'douglas', 'adams']
+
+filter.filter 'guide by douglas adams'.split
+# ['guide', 'douglas', 'adams']
+
+filter.stopword? 'by'
+# true
 ```
 
   2. Snowball version
@@ -37,7 +42,23 @@ filter.filter 'guide by douglas adams'.split #-> ['guide', 'douglas', 'adams']
 
 ```
 filter = Stopwords::Snowball::Filter.new "en"
-filter.filter 'guide by douglas adams'.split #-> ['guide', 'douglas', 'adams']
+filter.filter 'guide by douglas adams'.split
+# ['guide', 'douglas', 'adams']
+
+filter.stopword? 'by'
+# true
+```
+
+  2.1 Snowball version with Sieve class (thanks to @s2gatev)
+
+```ruby
+sieve = Stopwords::Snowball::WordSieve.new
+
+filtered = sieve.filter lang: :en, words: 'guide by douglas adams'.split
+# filtered = ['guide', 'douglas', 'adams']
+
+sieve.stopword? lang: :en, word: 'by'
+# true
 ```
 
 
@@ -103,6 +124,10 @@ Anything else?
 
 In a future version I would like to include a chaining filter where you include a series of operations and they are executed in a lineal order, just like the [Pipes and Filters design pattern][wikipedia_pipes_filters]
 
+Ackonowledgments
+----------------
+
+Thanks to @s2gatev who added the `stopword?` method and the sieve class to this gem
 
   [wikipedia_stopwords]: http://en.wikipedia.org/wiki/Stopword
   [solr]: https://github.com/sunspot/sunspot
@@ -110,4 +135,5 @@ In a future version I would like to include a chaining filter where you include
   [google]: https://github.com/alexreisner/google_custom_search
   [postgre]: https://github.com/Casecommons/pg_search
   [wikipedia_snowball]: http://en.wikipedia.org/wiki/Snowball_programming_language
-  [wikipedia_pipes_filters]: http://en.wikipedia.org/wiki/Pipes_and_filters
+  [wikipedia_pipes_filters]: http://en.wikipedia.org/wiki/Pipes_and_filters
+

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.2.0

data/lib/stopwords/filter.rb

@@ -10,4 +10,8 @@ class Stopwords::Filter
     words - @stopwords
   end
 
-end
+  def stopword? word
+    stopwords.include? word
+  end
+
+end

data/lib/stopwords/snowball.rb

@@ -1,3 +1,4 @@
 module Stopwords::Snowball
   require_relative 'snowball/filter'
+  require_relative 'snowball/wordsieve'
 end

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

@@ -0,0 +1 @@
+а,автентичен,аз,ако,ала,бе,без,беше,би,бивш,бивша,бившо,бил,била,били,било,благодаря,близо,бъдат,бъде,бяха,в,вас,ваш,ваша,вероятно,вече,взема,ви,вие,винаги,внимава,време,все,всеки,всички,всичко,всяка,във,въпреки,върху,г,ги,главен,главна,главно,глас,го,година,години,годишен,д,да,дали,два,двама,двамата,две,двете,ден,днес,дни,до,добра,добре,добро,добър,докато,докога,дори,досега,доста,друг,друга,други,е,евтин,едва,един,една,еднаква,еднакви,еднакъв,едно,екип,ето,живот,за,забавям,зад,заедно,заради,засега,заспал,затова,защо,защото,и,из,или,им,има,имат,иска,й,каза,как,каква,какво,както,какъв,като,кога,когато,което,които,кой,който,колко,която,къде,където,към,лесен,лесно,ли,лош,м,май,малко,ме,между,мек,мен,месец,ми,много,мнозина,мога,могат,може,мокър,моля,момента,му,н,на,над,назад,най,направи,напред,например,нас,не,него,нещо,нея,ни,ние,никой,нито,нищо,но,нов,нова,нови,новина,някои,някой,няколко,няма,обаче,около,освен,особено,от,отгоре,отново,още,пак,по,повече,повечето,под,поне,поради,после,почти,прави,пред,преди,през,при,пък,първата,първи,първо,пъти,равен,равна,с,са,сам,само,се,сега,си,син,скоро,след,следващ,сме,смях,според,сред,срещу,сте,съм,със,също,т,тази,така,такива,такъв,там,твой,те,тези,ти,т.н.,то,това,тогава,този,той,толкова,точно,три,трябва,тук,тъй,тя,тях,у,утре,харесва,хиляди,ч,часа,че,често,чрез,ще,щом,юмрук,я,як

data/lib/stopwords/snowball/wordsieve.rb

@@ -0,0 +1,16 @@
+class Stopwords::Snowball::WordSieve
+  def initialize
+    @filters = Dir[File.dirname(__FILE__) + '/locales/*.csv'].each_with_object({}) do |file, filters|
+      lang = File.basename(file, '.csv').to_sym
+      filters[lang] = Stopwords::Snowball::Filter.new lang
+    end
+  end
+
+  def stopword? args={}
+    args[:lang] ? @filters[args[:lang]].stopword?(args[:word] ) : false
+  end
+
+  def filter args={}
+    args[:lang] ? @filters[args[:lang]].filter(args[:words] ) : args[:words]
+  end
+end

metadata

@@ -2,7 +2,7 @@
 name: stopwords-filter
 version: !ruby/object:Gem::Version 
   prerelease: 
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors: 
 - David J. Brenes
@@ -20,9 +20,11 @@ executables: []
 extensions: []
 
 extra_rdoc_files: 
+- CHANGELOG
 - LICENSE.txt
 - README.md
 files: 
+- CHANGELOG
 - Gemfile
 - Gemfile.lock
 - README.md
@@ -31,6 +33,8 @@ files:
 - lib/stopwords/filter.rb
 - lib/stopwords/snowball.rb
 - lib/stopwords/snowball/filter.rb
+- lib/stopwords/snowball/wordsieve.rb
+- lib/stopwords/snowball/locales/bg.csv
 - lib/stopwords/snowball/locales/da.csv
 - lib/stopwords/snowball/locales/de.csv
 - lib/stopwords/snowball/locales/en.csv