summa 0.0.2 → 0.0.3

data/lib/summa.rb

@@ -2,12 +2,16 @@ $:.unshift(File.dirname(__FILE__)) unless
   $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
 
 module Summa
-  VERSION = '0.0.2'
+  VERSION = '0.0.3'
 end
 
 class String
-  def stem
-    puts "Still testing!... v0.0.2"
+  def summarize
+    puts "Moooore testing!... of Summa #{VERSION}"
+  end
+
+  def removePunctuation!
+    self.delete!(".,-:;()?!\"\'")
   end
 end
 
@@ -157,7 +161,8 @@ class FrequencyAnalyzer
 		for i in 0..@document.docArray.length
 			word = @document.docArray[i]
 			if word != nil
-				word = CGWordOps.removePunctuation(word)
+				#word = CGWordOps.removePunctuation(word)
+				word.delete!(".,;:()?!\"")
 				if !@stopWords.docArray.include?(word.downcase)
 					#stemmed = word.stem
 					if @freqCount.has_key?(word)
@@ -249,3 +254,330 @@ class CGDocument
 	
 end
 
+
+class SummaData
+
+@stopwords = Array.[]("a", \
+"about", \
+"above", \
+"across", \
+"after", \
+"afterwards", \
+"again", \
+"against", \
+"all", \
+"almost", \
+"alone", \
+"along", \
+"already", \
+"also", \
+"although", \
+"always", \
+"am", \
+"among", \
+"amongst", \
+"amoungst", \
+"amount", \
+"an", \
+"and", \
+"another", \
+"any", \
+"anyhow", \
+"anyone", \
+"anything", \
+"anyway", \
+"anywhere", \
+"are", \
+"around", \
+"as", \
+"at", \
+"back", \
+"be", \
+"became", \
+"because", \
+"become", \
+"becomes", \
+"becoming", \
+"been", \
+"before", \
+"beforehand", \
+"behind", \
+"being", \
+"below", \
+"beside", \
+"besides", \
+"between", \
+"beyond", \
+"bill", \
+"both", \
+"bottom", \
+"but", \
+"by", \
+"call", \
+"can", \
+"cannot", \
+"cant", \
+"co", \
+"computer", \
+"con", \
+"could", \
+"couldnt", \
+"cry", \
+"de", \
+"describe", \
+"detail", \
+"do", \
+"done", \
+"down", \
+"due", \
+"during", \
+"each", \
+"eg", \
+"eight", \
+"either", \
+"eleven", \
+"else", \
+"elsewhere", \
+"empty", \
+"enough", \
+"etc", \
+"even", \
+"ever", \
+"every", \
+"everyone", \
+"everything", \
+"everywhere", \
+"except", \
+"few", \
+"fifteen", \
+"fify", \
+"fill", \
+"find", \
+"fire", \
+"first", \
+"five", \
+"for", \
+"former", \
+"formerly", \
+"forty", \
+"found", \
+"four", \
+"from", \
+"front", \
+"full", \
+"further", \
+"get", \
+"give", \
+"go", \
+"had", \
+"has", \
+"hasnt", \
+"have", \
+"he", \
+"hence", \
+"her", \
+"here", \
+"hereafter", \
+"hereby", \
+"herein", \
+"hereupon", \
+"hers", \
+"herself", \
+"him", \
+"himself", \
+"his", \
+"how", \
+"however", \
+"hundred", \
+"i", \
+"ie", \
+"if", \
+"in", \
+"inc", \
+"indeed", \
+"interest", \
+"into", \
+"is", \
+"it", \
+"its", \
+"itself", \
+"keep", \
+"last", \
+"latter", \
+"latterly", \
+"least", \
+"less", \
+"ltd", \
+"made", \
+"many", \
+"may", \
+"me", \
+"meanwhile", \
+"might", \
+"mill", \
+"mine", \
+"more", \
+"moreover", \
+"most", \
+"mostly", \
+"move", \
+"much", \
+"must", \
+"my", \
+"myself", \
+"name", \
+"namely", \
+"neither", \
+"never", \
+"nevertheless", \
+"next", \
+"nine", \
+"no", \
+"nobody", \
+"none", \
+"noone", \
+"nor", \
+"not", \
+"nothing", \
+"now", \
+"nowhere", \
+"of", \
+"off", \
+"often", \
+"on", \
+"once", \
+"one", \
+"only", \
+"onto", \
+"or", \
+"other", \
+"others", \
+"otherwise", \
+"our", \
+"ours", \
+"ourselves", \
+"out", \
+"over", \
+"own", \
+"part", \
+"per", \
+"perhaps", \
+"please", \
+"put", \
+"rather", \
+"re", \
+"same", \
+"see", \
+"seem", \
+"seemed", \
+"seeming", \
+"seems", \
+"serious", \
+"several", \
+"she", \
+"should", \
+"show", \
+"side", \
+"since", \
+"sincere", \
+"six", \
+"sixty", \
+"so", \
+"some", \
+"somehow", \
+"someone", \
+"something", \
+"sometime", \
+"sometimes", \
+"somewhere", \
+"still", \
+"such", \
+"system", \
+"take", \
+"ten", \
+"than", \
+"that", \
+"the", \
+"their", \
+"them", \
+"themselves", \
+"then", \
+"thence", \
+"there", \
+"thereafter", \
+"thereby", \
+"therefore", \
+"therein", \
+"thereupon", \
+"these", \
+"they", \
+"thick", \
+"thin", \
+"third", \
+"this", \
+"those", \
+"though", \
+"three", \
+"through", \
+"throughout", \
+"thru", \
+"thus", \
+"to", \
+"together", \
+"too", \
+"top", \
+"toward", \
+"towards", \
+"twelve", \
+"twenty", \
+"two", \
+"un", \
+"under", \
+"until", \
+"up", \
+"upon", \
+"us", \
+"very", \
+"via", \
+"was", \
+"we", \
+"well", \
+"were", \
+"what", \
+"whatever", \
+"when", \
+"whence", \
+"whenever", \
+"where", \
+"whereafter", \
+"whereas", \
+"whereby", \
+"wherein", \
+"whereupon", \
+"wherever", \
+"whether", \
+"which", \
+"while", \
+"whither", \
+"who", \
+"whoever", \
+"whole", \
+"whom", \
+"whose", \
+"why", \
+"will", \
+"with", \
+"within", \
+"without", \
+"would", \
+"yet", \
+"you", \
+"your", \
+"yours", \
+"yourself", \
+"yourselves" )
+
+attr_accessor :stopwords
+end
+
+

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: summa
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  version: 0.0.3
 platform: ruby
 authors: 
 - HyLiter.org