raramorph 0.1.0 → 0.1.1

data/README

@@ -0,0 +1,56 @@
+== Raramorph
+By eSpace-technologies
+http://www.espace.com.eg
+http://www.espace.com.eg/docs/raramorph/index.html
+http://github.com/espace/raramorph
+http://raramorph.rubyforge.org
+
+== DESCRIPTION:
+
+Raramorph is a Ruby 1.9 gem for an intelligent port Aramorph based on Buckwalter Arabic Morphological Analyzer Version 1.0.
+
+== Usage
+
+ require 'raramorph'
+ # For analyzing a file
+  Raramorph.execute(input_filename, output_filename ,verbose = false, not_arabic = true)
+ # You can use functions like analyze_token , tokenize , segement_word  all as static methods in Raramorph class
+OR 
+From the command line
+raramorph input_file_name output_file_name  -v -a
+  -v verbose mode ( optional )
+  -a arabic output ( optional )
+
+ 
+  
+== INSTALL:
+
+sudo gem install raramorph
+
+=== Source Code =====
+http://github.com/espace/raramorph/tree/master
+
+== LICENSE:
+
+(The MIT License)
+
+Copyright (c) 2008 Moustafa Emara , Hany Salah el deen
+
+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.

data/lib/raramorph/arabic_latin_translator.rb

@@ -2,9 +2,7 @@
 # Author:: eSpace technologies  www.eSpace.com.eg
 # Copyright:: 2008
 #
-
 class ArabicLatinTranslator 
-  
   # * Table Used for Tranlation From Arabic To English I.e ( Romanize Word )
   # * According to  Buckwalter system Dictionary
   TABLE =   { "\u0621"=> "'" , "\u0622"=> "|" , "\u0623"=> ">" , "\u0624"=> "&" , "\u0625"=> "<" , "\u0626"=> "}" ,
@@ -20,9 +18,7 @@ class ArabicLatinTranslator
   #Not suitable for morphological analysis : remove all vowels/diacritics, i.e. undo the job !
   VOWEL_REMOVER = Regexp.compile("[FNKaui~o]")
   STRIPER =  Regexp.compile("[`\\{]")
- def initilaize
-   
- end
+
  
  # * Translate : Transilerate the arabic word to  Roman lettered Word
  # * [word] Word String To be processed

data/lib/raramorph/dictionary_entry.rb

@@ -1,7 +1,7 @@
 # Class For Storing Dictionary Entries
 # Author:: eSpace technologies  www.eSpace.com.eg
 # Copyright:: 2008
-#
+
 
 class DictionaryEntry
         ## Constructs a Dictionary Entry

data/lib/raramorph/in_memory_dictionary_handler.rb

@@ -1,7 +1,7 @@
 # Class For Storing And Loading Dictionaries
 # Author:: eSpace technologies  www.eSpace.com.eg
 # Copyright:: 2008
-#
+
 
 require 'rubygems'
 class InMemoryDictionaryHandler
@@ -25,25 +25,24 @@ class InMemoryDictionaryHandler
     ### Variables #####
       @@handler  = nil
       @@regex = Regexp.compile(".*" + "<pos>(.+?)</pos>" + ".*")
-      @@morphology_regexs=[]
-      #@@leema_starter = Regexp.compile(";; ")
-      @@morphology_regexs[0] = Regexp.compile("^(Pref-0|Suff-0)$")
-      @@morphology_regexs[1] = Regexp.compile("^F" + ".*")
-      @@morphology_regexs[2] = Regexp.compile("^IV" + ".*")
-      @@morphology_regexs[3] = Regexp.compile("^PV" + ".*")
-      @@morphology_regexs[4] = Regexp.compile("^CV" + ".*")
-      @@morphology_regexs[5] = Regexp.compile("^N" + ".*")
-      @@morphology_regexs[6] = Regexp.compile("^[A-Z]" + ".*")
-      @@morphology_regexs[7] = Regexp.compile(".*" + "iy~$")
+      @@morphology_regexs=[Regexp.compile("^(Pref-0|Suff-0)$") , 
+                           Regexp.compile("^F" + ".*") ,
+                           Regexp.compile("^IV" + ".*") ,
+                           Regexp.compile("^PV" + ".*") ,
+                           Regexp.compile("^CV" + ".*") ,
+                           Regexp.compile("^N" + ".*") , 
+                           Regexp.compile("^[A-Z]" + ".*") , 
+                           Regexp.compile(".*" + "iy~$") 
+                           ]  
       @@compatability_stpliter = Regexp.compile("\\s+")            
-      @@vocalization_array =[]
-      @@vocalization_array[0] = "/FUNC_WORD"
-      @@vocalization_array[1] ="/VERB_IMPERFECT"
-      @@vocalization_array[2] ="/VERB_PERFECT"
-      @@vocalization_array[3] ="/VERB_IMPERATIVE"
-      @@vocalization_array[4] = "/NOUN_PROP"
-      @@vocalization_array[5] ="/NOUN"
-      @@vocalization_array[6] = "/NOUN"
+      @@vocalization_array =["/FUNC_WORD" ,  
+                             "/VERB_IMPERFECT" , 
+                            "/VERB_PERFECT" , 
+                            "/VERB_IMPERATIVE" , 
+                            "/NOUN_PROP" ,
+                            "/NOUN" , 
+                            "/NOUN"
+                               ]
   
       @@prefixes_stems_compatibility = Set.new
     #Changed
@@ -163,6 +162,44 @@ class InMemoryDictionaryHandler
     @@suffixes = suffixes
   end
   
+  def analyze_word_in_dictionaries(segmented_word , word_solutions , verbose  , count)
+       #Is prefix known ?
+       if has_prefix?(segmented_word.prefix)
+         #Is stem known ?
+         # puts "has prefix"
+         if has_stem?(segmented_word.stem)
+          # puts "has stem"
+           #Is suffix known ?
+           if has_suffix?(segmented_word.suffix)
+           #  puts "has suffix"
+             #Compatibility check
+              @@prefixes[segmented_word.prefix].each{|prefix|
+                @@stems[segmented_word.stem].each {|stem|
+                  #Prefix/Stem compatibility
+                    if prefixes_stems_compatible?(prefix.morphology ,stem.morphology )
+                      # puts "has A B Com" 
+                      @@suffixes[segmented_word.suffix].each {|suffix|
+                       # Prefix/Suffix compatiblity
+                       if prefixes_suffixes_compatible?(prefix.morphology , suffix.morphology)
+                         # puts "has A C Com"
+                          # Stems/Suffixes compatiblity
+                         if stems_suffixes_compatible?(stem.morphology , suffix.morphology)
+                          # puts "has  B  C COM"
+                            #All tests passed : it is a solution
+                            count = count + 1
+                            word_solutions << Solution.new(verbose , count , prefix , stem , suffix )
+                         end
+                       end
+                      }
+                    end
+                }
+              }
+           end
+         end
+       end
+	   return count
+  end
+  
  private 
  
   # * load Dictionary from files  
@@ -241,7 +278,8 @@ class InMemoryDictionaryHandler
              vocalization = splited_line[1]
              morphology = splited_line[2]
              gloss_pos = splited_line[3]
-             gloss , pos = "" 
+             gloss = ""
+             pos = "" 
              # two ways to get the POS info
              # (1) explicitly, by extracting it from the gloss field:
             

data/lib/raramorph/in_memory_solutions_handler.rb

@@ -2,7 +2,7 @@
 # 
 # Author:: eSpace technologies  www.eSpace.com.eg
 # Copyright:: 2008
-#
+
 
 class InMemorySolutionsHandler
   

data/lib/raramorph/latin_arabic_translator.rb

@@ -1,7 +1,7 @@
 # Class For  Latin Arabic Transileration
 # Author:: eSpace technologies  www.eSpace.com.eg
 # Copyright:: 2008
-#
+
 
 class LatinArabicTranslator
   

data/lib/raramorph/logger.rb

@@ -0,0 +1,20 @@
+class Logger
+
+
+  attr_reader :verbose , :output
+  def initialize(verbose = nil  , output = nil )
+     @verbose = verbose
+	 @output = output
+	 @stream = StringIO.new
+  end
+  
+  def info string , require_verbose = false
+    @stream.puts(string) #if (  require_verbose && @verbose  || ! require_verbose )  
+  end
+  
+  def log
+    return  puts @stream.string  if @output.nil? 
+	File.open(@output , "w") { |f| 
+	 f.puts @stream.string }
+  end  
+end

data/lib/raramorph/raramorph.rb

@@ -1,10 +1,8 @@
-# A Ruby port of Buckwalter Arabic Morphological Analyzer Version 1.0.
-# 
+# A Ruby port of Buckwalter  Morphological Analyzer Version 1.0. 
 # Author:: eSpace technologies  www.eSpace.com.eg
 # Copyright:: 2008
 
 
-require 'set'
 
 class Raramorph
 
@@ -13,48 +11,14 @@ class Raramorph
   # The solutions handler.
   @@sol = InMemorySolutionsHandler.create
   # Whether or not the analyzer should output some convenience messages 
-  @verbose
-  # The stream where to output the results 
-
-  @output_stream
-  
-  #use arabic translation or not?
-  @not_arabic
-  
-  #Stats
-  # Lines processed
-   @lines_counter = 0
-  # Arabic tokens processed
-   @not_arabic_tokens_counter = 0
-  # Not arabic tokens processed 
-   @not_arabic_tokens_counter = 0
-
-  # Arabic words which have been succesfully analyzed.
-  # * [key] = word
-  # * [value] = occurences
-  #
-   @found = {}
-
-  # Arabic words which have not been succesfully analyzed.
-  # * [key] = word
-  # * [value] = occurences
-  #
-   @not_found = {}   
-  
   # Alternative spellings list of regular expressions
-  @@alternative_spellings = []
-  @@alternative_spellings[0] = Regexp.compile(".*" + "Y'$")
-  @@alternative_spellings[1] = Regexp.compile(".*" + "y'$")
-  @@alternative_spellings[2] = Regexp.compile(".*" + "y$")
-  @@alternative_spellings[3] = Regexp.compile(".*" + "h$")
-  @@alternative_spellings[4] = Regexp.compile(".*" + "p$")
+  @@alternative_spellings = [Regexp.compile(".*" + "Y'$") ,  
+                             Regexp.compile(".*" + "y'$") , 
+                             Regexp.compile(".*" + "y$") , 
+                             Regexp.compile(".*" + "h$") , 
+                             Regexp.compile(".*" + "p$") ]
   @@space_regex = Regexp.compile("\\s+")
      
-    
-  def self.set_verbose(verbose) #Bolean Variable
-    @verbose = verbose
-  end
-  
   # * Analyze and Process the file ( i.e Doing the morphological Analysis )
   # * [file_reader_in] Input File Path
   # * [output_buckwalter] whether the output in buckwalter indications ( i.e Roman letters ) or arabic letters
@@ -63,8 +27,8 @@ class Raramorph
      lines= IO.readlines(file_reader_in)
       lines.each do |line|
         @lines_counter+=1
-        if(@verbose)
-           puts "Processing line : "+ @lines_counter.to_s
+        if(@logger.verbose)
+           puts "Processing line : #{@lines_counter.to_s}"
         end
         tokens = tokenize(line)
         tokens.each do |token|
@@ -72,7 +36,7 @@ class Raramorph
         end 
       end
     #rescue
-    #  @stream.puts "Can not read line " + @lines_counter.to_s
+    #  @logger.info "Can not read line " + @lines_counter.to_s
     #end    
   end
   
@@ -102,7 +66,7 @@ class Raramorph
   def self.analyze_token(token ,  output_buckwalter) #STring  , Boolean , REturn Boolean
      #TO DO SET UP THE PRINT STREAM
      token.force_encoding "UTF-8"
-     @stream.puts "Processing token : " + "\t" + token
+     @logger.info "Processing token : " + "\t" + token
      #TODO : check accuracy
      #ignored \u0688 : ARABIC LETTER DDAL
      #ignored \u06A9 : ARABIC LETTER KEHEH
@@ -119,7 +83,7 @@ class Raramorph
           sub_tokens.each{|sub_token|
             unless  sub_token.strip == ""  
               @not_arabic_tokens_counter+=1
-              @output_stream != nil ? @stream.puts("Non-Arabic : " + sub_token) : puts("Non-Arabic : " + sub_token)
+              @logger.info("Non-Arabic : #{sub_token}")
             end 
           }
           return false
@@ -128,31 +92,30 @@ class Raramorph
        @not_arabic_tokens_counter+=1
        
        translitered = ArabicLatinTranslator.translate(token)
-       @output_stream != nil ? @stream.puts("Transliteration : " + "\t" + translitered) : puts("Transliteration : " + "\t" + translitered)
+       @logger.info("Transliteration : \t#{translitered}")
 
       if @found.has_key?(translitered)        #Already processed : previously found
-        @output_stream != nil  && @verbose ? @stream.puts("Token already processed.") : puts("Token already processed.")          
+        @logger.info("Token already processed." , true )         
         #increase reference counter
         @found[translitered]+=1
         has_solutions = true
        elsif @not_found.has_key?(translitered) #Already processed : previously not found  
-        @output_stream != nil  && @verbose ? @stream.puts("Token already processed without solution.") : puts("Token already processed without solution.")          
+        @logger.info("Token already processed without solution." , true )
         @not_found[translitered]+=1         #increase reference counter
         has_solutions = false
        else
-        @output_stream != nil  && @verbose ? @stream.puts("Token not yet processed.") : puts("Token not yet processed.")          
+        @logger.info("Token not yet processed.", true )
 
         if (feed_word_solutions(translitered)) #CHANGED  #word has solutions...
           #mark word as found
           raise "There is already a key for " + translitered + " in found" if @found.has_key?(translitered)
-          @output_stream != nil  && @verbose ? @stream.puts("Token has direct solutions.") : puts("Token has direct solutions.")          
+          @logger.info("Token has direct solutions." , true )
           #set reference counter to 1
           @found[translitered] = 1
           has_solutions = true
         else #word has no direct solution
            if(feed_alternative_spellings(translitered))
              alternatives_give_solutions = false
-             
              alternatives = @@sol.get_alternative_spellings(translitered)
              alternatives.each{|alternative|
               alternatives_give_solutions =  (alternatives_give_solutions || feed_word_solutions(alternative))
@@ -160,21 +123,21 @@ class Raramorph
              if(alternatives_give_solutions)
                #consistency check
                raise "There is already a key for " + translitered + " in found" if @found.has_key?(translitered)
-               @output_stream != nil  && @verbose ? @stream.puts("Token's alternative spellings have solutions.") : puts("Token's alternative spellings have solutions.")
+               @logger.info("Token's alternative spellings have solutions." , true )
                #mark word as found set reference counter to 1
                @found[translitered] = 1
                has_solutions = true
              else
                #consistency check
                raise "There is already a key for " + translitered + " in notFound" if @not_found.has_key?(translitered)
-               @output_stream != nil  && @verbose ? @stream.puts("Token's alternative spellings have no solution.") : puts("Token's alternative spellings have no solution.")
+               @logger.info("Token's alternative spellings have no solution." , true )
                @not_found[translitered]=1 
                has_solutions = false  
            end
          else
            #there are no alternative
            raise "There is already a key for " + translitered + " in notFound" if @not_found.has_key?(translitered)
-           @output_stream != nil  && @verbose ? @stream.puts("Token has no solution and no alternative spellings.") : puts("Token has no solution and no alternative spellings.")
+           @logger.info("Token has no solution and no alternative spellings." , true )
            #mark word as not found and set reference counter to 1
            @not_found[translitered]=1 
            has_solutions = false  
@@ -184,22 +147,24 @@ class Raramorph
       
       
         #output solutions : TODO consider XML output
-        if @output_stream != nil
+        if @logger.output != nil
           if @found.has_key?(translitered)
             if @@sol.has_solutions(translitered)
-              @@sol.get_solutions(translitered).each{|solution| @stream.puts "#{output_buckwalter ? solution.to_s : solution.to_arabized_string}"}
+              @@sol.get_solutions(translitered).each{|solution| @logger.info "#{output_buckwalter ? solution.to_s : solution.to_arabized_string}" 
+			  }
             end
             if @@sol.has_alternative_spellings(translitered) 
-              @output_stream != nil  && @verbose ? @stream.puts("No direct solution") : puts("No direct solution")   
+              @logger.info("No direct solution" , true )
               @@sol.get_alternative_spellings(translitered).each{|alternative| 
-                 @output_stream != nil  && @verbose ? @stream.puts("Considering alternative spelling :" + "\t" + alternative) : puts("Considering alternative spelling :" + "\t" + alternative)   
+               @logger.info("Considering alternative spelling :" + "\t#{alternative}" , true )
                  if @@sol.has_solutions(alternative)
-                   @@sol.get_solutions(alternative).each{|solution| @stream.puts "#{output_buckwalter ? solution.to_s : solution.to_arabized_string}"}
+                   @@sol.get_solutions(alternative).each{|solution| @logger.info "#{output_buckwalter ? solution.to_s : solution.to_arabized_string}"
+				   }
                  end
               }
             end            
           elsif @not_found.has_key?(translitered)
-            @stream.puts "\nNo solution\n"
+            @logger.info "\nNo solution\n"
           else
             raise "#{translitered} is neither in found or notFound !" 
           end
@@ -220,40 +185,7 @@ class Raramorph
      segments = segment_word(translitered) #Hash Set of Segement Words Objects
      #Brute force algorithm
      segments.each{|segmented_word|
-       #Is prefix known ?
-       if @@dict.has_prefix?(segmented_word.prefix)
-         #Is stem known ?
-         # puts "has prefix"
-         if @@dict.has_stem?(segmented_word.stem)
-          # puts "has stem"
-           #Is suffix known ?
-           if @@dict.has_suffix?(segmented_word.suffix)
-           #  puts "has suffix"
-             #Compatibility check
-              @@dict.prefixes[segmented_word.prefix].each{|prefix|
-                @@dict.stems[segmented_word.stem].each {|stem|
-                  #Prefix/Stem compatibility
-                    if @@dict.prefixes_stems_compatible?(prefix.morphology ,stem.morphology )
-                      # puts "has A B Com" 
-                      @@dict.suffixes[segmented_word.suffix].each {|suffix|
-                       # Prefix/Suffix compatiblity
-                       if @@dict.prefixes_suffixes_compatible?(prefix.morphology , suffix.morphology)
-                         # puts "has A C Com"
-                          # Stems/Suffixes compatiblity
-                         if @@dict.stems_suffixes_compatible?(stem.morphology , suffix.morphology)
-                          # puts "has  B  C COM"
-                            #All tests passed : it is a solution
-                            count = count + 1
-                            word_solutions << Solution.new(@verbose , count , prefix , stem , suffix )
-                         end
-                       end
-                      }
-                    end
-                }
-              }
-           end
-         end
-       end
+	   count  = @@dict.analyze_word_in_dictionaries(segmented_word , word_solutions , @logger.verbose , count )
      }
     
       #Add all solutions, if any
@@ -322,37 +254,29 @@ class Raramorph
   # * Find Alternative Spellings for the translitered word
   # * [translitered] word to be proccesed
   def self.feed_alternative_spellings(translitered)
-            return true  if(@@sol.has_alternative_spellings(translitered))
+    return true  if(@@sol.has_alternative_spellings(translitered))
     word_alternative_spellings = Set.new
     temp = translitered
     
     if( temp.match(@@alternative_spellings[0]) )
       temp.gsub!(/Y/, "y")
-      if(@verbose)
-        @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-      end
+      @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
       word_alternative_spellings.add(temp)
       temp2 = temp.sub(/w/, "&")
       if(temp!=temp2)
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info  "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       temp=translitered
       temp.gsub!(/Y/,"y")
       temp.sub!(/y'$/,"}")
-      if(@verbose)
-        @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-      end
+      @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
       word_alternative_spellings.add(temp)
       temp2 = temp.sub(/w/, "&")
       if(temp!=temp2)
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       
@@ -360,32 +284,24 @@ class Raramorph
       temp2 = temp.gsub(/Y/,"y")
       if(temp != temp2 )
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       temp2 = temp.sub(/w'/, "&")
       if(temp != temp2 )
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       temp =translitered
       temp.gsub!(/Y/, "y")
       temp.sub!(/y'$/, "}")
-      if(@verbose)
-        @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-      end
+      @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
       word_alternative_spellings.add(temp)
       temp2 = temp.sub(/w'/, "&")
       if(temp != temp2 )
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       
@@ -394,24 +310,18 @@ class Raramorph
       temp2 = temp.sub(/w'/, "&")
       if(temp != temp2 )
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       temp =translitered
       temp.gsub!(/Y/, "y")
       temp.gsub!(/y$/, "Y")
-      if(@verbose)
-        @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-      end
+      @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
       word_alternative_spellings.add(temp)
       temp2 = temp.sub(/w'/, "&")
       if(temp != temp2 )
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       
@@ -419,23 +329,17 @@ class Raramorph
       temp2 = temp.gsub(/Y/,"y")
       if(temp != temp2 )
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       temp2 = temp.sub(/w'/, "&")
       if(temp != temp2 )
         temp = temp2
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
       end
       temp.sub!(/p$/, "h")
-      if(@verbose)
-        @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-      end
+      @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
       word_alternative_spellings.add(temp)
     
     else
@@ -443,40 +347,30 @@ class Raramorph
       if(temp!=temp2)
         temp = temp2
         temp.gsub!(/Y/, "y")
-        if(@verbose)
-          @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-        end
+        @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
         word_alternative_spellings.add(temp)
         temp2 = temp.sub(/w'/, "&")
         if(temp != temp2 )
           temp = temp2
-          if(@verbose)
-            @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-          end
+          @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
           word_alternative_spellings.add(temp)
         end
       else
         temp2 = temp.gsub(/Y/, "y")
         if(temp != temp2)
-          if(@verbose)
-            @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-          end
+           @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
           word_alternative_spellings.add(temp)
           temp2 = temp.sub(/w'/, "&")
           if(temp != temp2 )
             temp = temp2
-            if(@verbose)
-              @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-            end
+            @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
             word_alternative_spellings.add(temp)
           end   
         else
           temp2 = temp.sub(/w'/, "&")   
           if(temp != temp2 )
             temp = temp2
-            if(@verbose)
-              @stream.puts "Found alternative spelling "+ temp + " for word " + translitered
-            end
+            @logger.info "Found alternative spelling #{temp} for word #{translitered}" , true
             word_alternative_spellings.add(temp)
           end      
         end
@@ -494,10 +388,9 @@ class Raramorph
   # * [output_filename] Output file path
   # * [verbose] Setter for verbose
   # * [not_arabic] alias for out_put_bucwalter for indicating the output format  in buckwalter indications or will be arabic 
-  def self.execute(input_filename, output_filename ,verbose = false, not_arabic = true)
-    @output_stream = true
+  def self.execute(input_filename, output_filename ,verbose = false, not_arabic = false)
+    @logger = Logger.new(true , output_filename )
     @not_arabic = not_arabic
-    @verbose = verbose
     # Lines processed
     @lines_counter = 0
     # Arabic tokens processed
@@ -514,24 +407,11 @@ class Raramorph
     # * [value] = occurences
     #
     @not_found = {}
-    @stream = StringIO.new
-    
     analyze(input_filename , @not_arabic) 
-    File.open(output_filename , "w") do |f|
-      f.puts @stream.string
-    end
+    @logger.log
      print_stats
   end
  end  
  
-  class SegmentedWord
-    # Class For  Storing the Data of segmented Word
-    # Author:: eSpace technologies  www.eSpace.com.eg
-    # Copyright:: 2008
-    attr_reader :prefix , :stem , :suffix
-    def initialize(prefix , stem , suffix)
-      @prefix = prefix
-      @stem = stem
-      @suffix = suffix
-    end
-  end
+ class SegmentedWord < Struct.new( :prefix , :stem , :suffix) ; end 
+

data/lib/raramorph/solution.rb

@@ -1,14 +1,47 @@
 # A class to find the solution of the word
-# 
 # Author:: eSpace technologies  www.eSpace.com.eg
 # Copyright:: 2008
-#
+
 
 
 class Solution
   
   attr_reader :prefix, :stem, :suffix, :cnt
+  @@ends_with_set_for_pos_one = Set.new(["CONJ","EMPHATIC_PARTICLE","FUNC_WORD",
+                "FUT_PART","INTERJ","INTERROG_PART","IV1S","IV2MS",
+                "IV2FS","IV3MS","IV3FS","IV2D","IV2FD","IV3MD","IV3FD",
+                "IV1P","IV2MP","IV2FP","IV3MP","IV3FP","NEG_PART",
+                "PREP","RESULT_CLAUSE_PARTICLE"])
   
+  @@ends_with_set_for_pos_two = Set.new(["CASE_INDEF_NOM","CASE_INDEF_ACC",
+                "CASE_INDEF_ACCGEN","CASE_INDEF_GEN" ,"CASE_DEF_NOM" ,
+                "CASE_DEF_ACC" ,"CASE_DEF_ACCGEN","CASE_DEF_GEN" ,
+                "NSUFF_MASC_SG_ACC_INDEF" ,"NSUFF_FEM_SG" ,"NSUFF_MASC_DU_NOM" ,
+                "NSUFF_MASC_DU_NOM_POSS" ,"NSUFF_MASC_DU_ACCGEN" ,
+                "NSUFF_MASC_DU_ACCGEN_POSS" ,"NSUFF_FEM_DU_NOM" ,
+                "NSUFF_FEM_DU_NOM_POSS" ,"NSUFF_FEM_DU_ACCGEN" ,
+                "NSUFF_FEM_DU_ACCGEN_POSS" ,"NSUFF_MASC_PL_NOM" ,
+                "NSUFF_MASC_PL_NOM_POSS"  ,"NSUFF_MASC_PL_ACCGEN" ,
+                "NSUFF_MASC_PL_ACCGEN_POSS" ,"NSUFF_FEM_PL" ,"POSS_PRON_1S",
+                "POSS_PRON_2MS" ,"POSS_PRON_2FS" ,"POSS_PRON_3MS"  ,
+                "POSS_PRON_3FS","POSS_PRON_2D" ,"POSS_PRON_3D" ,"POSS_PRON_1P",
+                "POSS_PRON_2MP" ,"POSS_PRON_2FP" ,"POSS_PRON_3MP" ,"POSS_PRON_3FP" ,
+                "IVSUFF_DO:1S" ,"IVSUFF_DO:2MS" ,"IVSUFF_DO:2FS" ,"IVSUFF_DO:3MS" ,
+                "IVSUFF_DO:3FS" ,"IVSUFF_DO:2D" ,"IVSUFF_DO:3D" ,"IVSUFF_DO:1P" ,
+                "IVSUFF_DO:2MP" ,"IVSUFF_DO:2FP" ,"IVSUFF_DO:3MP" ,"IVSUFF_DO:3FP" ,
+                "IVSUFF_MOOD:I" ,"IVSUFF_SUBJ:2FS_MOOD:I" ,"IVSUFF_SUBJ:D_MOOD:I" ,
+                "IVSUFF_SUBJ:3D_MOOD:I" ,"IVSUFF_SUBJ:MP_MOOD:I" ,"IVSUFF_MOOD:S",
+                "IVSUFF_SUBJ:2FS_MOOD:SJ" ,"IVSUFF_SUBJ:D_MOOD:SJ","IVSUFF_SUBJ:MP_MOOD:SJ" ,
+                "IVSUFF_SUBJ:3MP_MOOD:SJ" ,"IVSUFF_SUBJ:FP" ,"PVSUFF_DO:1S" ,"PVSUFF_DO:2MS" ,
+                "PVSUFF_DO:2FS" ,"PVSUFF_DO:3MS" ,"PVSUFF_DO:3FS" ,"PVSUFF_DO:2D" ,
+                "PVSUFF_DO:3D" ,"PVSUFF_DO:1P" ,"PVSUFF_DO:2MP" ,"PVSUFF_DO:2FP" ,
+                "PVSUFF_DO:3MP" ,"PVSUFF_DO:3FP" ,"PVSUFF_SUBJ:1S" ,"PVSUFF_SUBJ:2MS" ,
+                "PVSUFF_SUBJ:2FS" ,"PVSUFF_SUBJ:3MS" ,"PVSUFF_SUBJ:3FS" ,"PVSUFF_SUBJ:2MD" ,
+                "PVSUFF_SUBJ:2FD" ,"PVSUFF_SUBJ:3MD" ,"PVSUFF_SUBJ:3FD" ,"PVSUFF_SUBJ:1P" ,
+                "PVSUFF_SUBJ:2MP" ,"PVSUFF_SUBJ:2FP" ,"PVSUFF_SUBJ:3MP" ,"PVSUFF_SUBJ:3FP" ,
+                "CVSUFF_DO:1S" ,"CVSUFF_DO:3MS" ,"CVSUFF_DO:3FS" ,"CVSUFF_DO:3D" ,
+                "CVSUFF_DO:1P" ,"CVSUFF_DO:3MP" ,"CVSUFF_DO:3FP" ,"CVSUFF_SUBJ:2MS" ,
+                "CVSUFF_SUBJ:2FS" ,"CVSUFF_SUBJ:2MP"])				
   protected
     
   # Constructs a solution for a word. Note that the prefix, stem and suffix combination is <b>recomputed</b> 
@@ -42,60 +75,35 @@ class Solution
       @stemsGlosses = stem.glosses
       #The suffixes glosses.
       @suffixesGlosses = suffix.glosses
-      
-    if (@stemsPOS.length != @stemsGlosses.length)
-        if (@debug) 
-          puts "\"" + get_lemma() + "\" : stem's sizes for POS (" + @stemsPOS.length.to_s + ") and GLOSS ("+ @stemsGlosses.length.to_s + ") do not match"
-        end
-      end            				
-      
+           
+      puts "\"#{get_lemma()}\" : stem's sizes for POS (\"#{@stemsPOS.length.to_s}\") and GLOSS (\"#{@stemsGlosses.length.to_s}\") do not match" if (@stemsPOS.length != @stemsGlosses.length and @debug)
+    
       #Normalize stems since some of them can contain prefixes
     
       while(@stemsPOS.length>0)
               stemPOS = @stemsPOS.slice(0)
-              if(stemPOS)
-                stemPOS.force_encoding "UTF-8"
-              end
+             
+              stemPOS.force_encoding "UTF-8" if(stemPOS)
+         
               if (@stemsGlosses.length>0) 
                 stemGloss = @stemsGlosses.slice(0)
               else 
                 stemGloss = nil
               end
-              if(stemGloss)
-                stemGloss.force_encoding "UTF-8"
-              end
-              if (stemPOS.end_with?("CONJ") or 
-                    stemPOS.end_with?("EMPHATIC_PARTICLE") or 
-                    stemPOS.end_with?("FUNC_WORD") or 
-                    stemPOS.end_with?("FUT_PART") or 
-                    stemPOS.end_with?("INTERJ") or 
-                    stemPOS.end_with?("INTERROG_PART") or 
-                    stemPOS.end_with?("IV1S") or 
-                    stemPOS.end_with?("IV2MS") or 
-                    stemPOS.end_with?("IV2FS") or 
-                    stemPOS.end_with?("IV3MS") or 
-                    stemPOS.end_with?("IV3FS") or 
-                    stemPOS.end_with?("IV2D") or 
-                    stemPOS.end_with?("IV2FD") or 
-                    stemPOS.end_with?("IV3MD") or 
-                    stemPOS.end_with?("IV3FD") or 
-                    stemPOS.end_with?("IV1P") or 
-                    stemPOS.end_with?("IV2MP") or 
-                    stemPOS.end_with?("IV2FP") or 
-                    stemPOS.end_with?("IV3MP") or 
-                    stemPOS.end_with?("IV3FP") or 
-                    stemPOS.end_with?("NEG_PART") or 
-                    stemPOS.end_with?("PREP") or 
-                    stemPOS.end_with?("RESULT_CLAUSE_PARTICLE") ) 
+             
+              stemGloss.force_encoding "UTF-8" if(stemGloss)
+              
+              
+                 if(stemPOS.ends_with_suffix_set?(@@ends_with_set_for_pos_one) )
                       @stemsPOS.slice!(0)
                       @prefixesPOS.push(stemPOS)
                       if (stemGloss) 
                         @stemsGlosses.slice!(0)
                         @prefixesGlosses.push(stemGloss)
                       end
-              else 
-                      break					
-              end
+                 else
+                   break
+                 end
       end              
       
       #Normalize stems since some of them can contain suffixes    
@@ -112,101 +120,8 @@ class Solution
               if(stemGloss)
                 stemGloss.force_encoding "UTF-8"
               end
-              
-              if (stemPOS.end_with?("CASE_INDEF_NOM") or 
-                    stemPOS.end_with?("CASE_INDEF_ACC") or 
-                    stemPOS.end_with?("CASE_INDEF_ACCGEN") or 
-                    stemPOS.end_with?("CASE_INDEF_GEN") or 
-                    stemPOS.end_with?("CASE_DEF_NOM") or 
-                    stemPOS.end_with?("CASE_DEF_ACC") or 
-                    stemPOS.end_with?("CASE_DEF_ACCGEN") or 
-                    stemPOS.end_with?("CASE_DEF_GEN") or 
-                    stemPOS.end_with?("NSUFF_MASC_SG_ACC_INDEF") or 
-                    stemPOS.end_with?("NSUFF_FEM_SG") or 
-                    stemPOS.end_with?("NSUFF_MASC_DU_NOM") or 
-                    stemPOS.end_with?("NSUFF_MASC_DU_NOM_POSS") or 
-                    stemPOS.end_with?("NSUFF_MASC_DU_ACCGEN") or 
-                    stemPOS.end_with?("NSUFF_MASC_DU_ACCGEN_POSS") or 
-                    stemPOS.end_with?("NSUFF_FEM_DU_NOM") or 
-                    stemPOS.end_with?("NSUFF_FEM_DU_NOM_POSS") or 
-                    stemPOS.end_with?("NSUFF_FEM_DU_ACCGEN") or 
-                    stemPOS.end_with?("NSUFF_FEM_DU_ACCGEN_POSS") or 
-                    stemPOS.end_with?("NSUFF_MASC_PL_NOM") or 
-                    stemPOS.end_with?("NSUFF_MASC_PL_NOM_POSS") or 
-                    stemPOS.end_with?("NSUFF_MASC_PL_ACCGEN") or 
-                    stemPOS.end_with?("NSUFF_MASC_PL_ACCGEN_POSS") or 
-                    stemPOS.end_with?("NSUFF_FEM_PL") or 
-                    stemPOS.end_with?("POSS_PRON_1S") or 
-                    stemPOS.end_with?("POSS_PRON_2MS") or 
-                    stemPOS.end_with?("POSS_PRON_2FS") or 
-                    stemPOS.end_with?("POSS_PRON_3MS") or 
-                    stemPOS.end_with?("POSS_PRON_3FS") or 
-                    stemPOS.end_with?("POSS_PRON_2D") or 
-                    stemPOS.end_with?("POSS_PRON_3D") or 
-                    stemPOS.end_with?("POSS_PRON_1P") or 
-                    stemPOS.end_with?("POSS_PRON_2MP") or 
-                    stemPOS.end_with?("POSS_PRON_2FP") or 
-                    stemPOS.end_with?("POSS_PRON_3MP") or 
-                    stemPOS.end_with?("POSS_PRON_3FP") or 
-                    stemPOS.end_with?("IVSUFF_DO:1S") or 
-                    stemPOS.end_with?("IVSUFF_DO:2MS") or 
-                    stemPOS.end_with?("IVSUFF_DO:2FS") or 
-                    stemPOS.end_with?("IVSUFF_DO:3MS") or 
-                    stemPOS.end_with?("IVSUFF_DO:3FS") or 
-                    stemPOS.end_with?("IVSUFF_DO:2D") or 
-                    stemPOS.end_with?("IVSUFF_DO:3D") or 
-                    stemPOS.end_with?("IVSUFF_DO:1P") or 
-                    stemPOS.end_with?("IVSUFF_DO:2MP") or 
-                    stemPOS.end_with?("IVSUFF_DO:2FP") or 
-                    stemPOS.end_with?("IVSUFF_DO:3MP") or 
-                    stemPOS.end_with?("IVSUFF_DO:3FP") or 
-                    stemPOS.end_with?("IVSUFF_MOOD:I") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:2FS_MOOD:I") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:D_MOOD:I") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:3D_MOOD:I") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:MP_MOOD:I") or 
-                    stemPOS.end_with?("IVSUFF_MOOD:S") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:2FS_MOOD:SJ") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:D_MOOD:SJ") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:MP_MOOD:SJ") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:3MP_MOOD:SJ") or 
-                    stemPOS.end_with?("IVSUFF_SUBJ:FP") or 
-                    stemPOS.end_with?("PVSUFF_DO:1S") or 
-                    stemPOS.end_with?("PVSUFF_DO:2MS") or 
-                    stemPOS.end_with?("PVSUFF_DO:2FS") or 
-                    stemPOS.end_with?("PVSUFF_DO:3MS") or 
-                    stemPOS.end_with?("PVSUFF_DO:3FS") or 
-                    stemPOS.end_with?("PVSUFF_DO:2D") or 
-                    stemPOS.end_with?("PVSUFF_DO:3D") or 
-                    stemPOS.end_with?("PVSUFF_DO:1P") or 
-                    stemPOS.end_with?("PVSUFF_DO:2MP") or 
-                    stemPOS.end_with?("PVSUFF_DO:2FP") or 
-                    stemPOS.end_with?("PVSUFF_DO:3MP") or 
-                    stemPOS.end_with?("PVSUFF_DO:3FP") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:1S") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:2MS") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:2FS") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:3MS") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:3FS") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:2MD") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:2FD") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:3MD") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:3FD") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:1P") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:2MP") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:2FP") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:3MP") or 
-                    stemPOS.end_with?("PVSUFF_SUBJ:3FP") or 
-                    stemPOS.end_with?("CVSUFF_DO:1S") or 
-                    stemPOS.end_with?("CVSUFF_DO:3MS") or 
-                    stemPOS.end_with?("CVSUFF_DO:3FS") or 
-                    stemPOS.end_with?("CVSUFF_DO:3D") or 
-                    stemPOS.end_with?("CVSUFF_DO:1P") or 
-                    stemPOS.end_with?("CVSUFF_DO:3MP") or 
-                    stemPOS.end_with?("CVSUFF_DO:3FP") or 
-                    stemPOS.end_with?("CVSUFF_SUBJ:2MS") or 
-                    stemPOS.end_with?("CVSUFF_SUBJ:2FS") or 
-                    stemPOS.end_with?("CVSUFF_SUBJ:2MP")  ) 
+                
+              if(stemPOS.ends_with_suffix_set?(@@ends_with_set_for_pos_two))
                       @stemsPOS.slice!(@stemsPOS.length-1)
                       @suffixesPOS.insert(0,stemPOS)
                       if (stemGloss) 
@@ -332,14 +247,10 @@ class Solution
     sb = ""
     sb.force_encoding "UTF-8"
     vocal = get_prefixes_arabic_vocalizations()
-    if(vocal!=nil)
-      sb += vocal[0].to_s
-    end
+      sb += vocal[0].to_s if vocal!=nil    
     
-    s = get_stem_arabic_vocalization() 
-    if ( s != nil) 
-      sb+=s
-    end
+    s = get_stem_arabic_vocalization()     
+      sb+=s if s!= nil
     vocal = get_suffixes_arabic_vocalizations()    
     if(vocal!=nil)
       sb += vocal[0].to_s
@@ -376,13 +287,13 @@ class Solution
     sb = ""
     sb.force_encoding "UTF-8"
     if (!@prefix.morphology.empty? and @prefix.morphology != nil )
-          sb+= "\t" + "prefix : " + @prefix.morphology + "\n"
+          sb+= "\tprefix : #{@prefix.morphology}\n"
     end
     if (!@stem.morphology.empty? and @stem.morphology != nil)
-          sb+= "\t" + "stem : " + @stem.morphology + "\n"
+          sb+= "\tstem : #{@stem.morphology}\n"
     end
     if (!@suffix.morphology.empty? and @suffix.morphology != nil)
-          sb+= "\t" + "suffix : " + @suffix.morphology + "\n"
+          sb+= "\tsuffix : #{@suffix.morphology}\n"
     end
     return sb
    end
@@ -517,14 +428,14 @@ class Solution
     sb.force_encoding "UTF-8"
     glosses = get_prefixes_glosses()
     if (glosses and glosses[0] != nil) 
-          sb+=("\t" + "prefix : " + glosses[0].gsub(";","/") + "\n")	        
+          sb+=("\tprefix : #{glosses[0].gsub(";","/")}\n")	        
     end
     if (get_stem_gloss() != nil) 
-      sb+=("\t" + "stem : " +get_stem_gloss().gsub(";","/") + "\n")	
+      sb+=("\tstem : #{get_stem_gloss().gsub(";","/")}\n")	
     end
     glosses = get_suffixes_glosses()
     if (glosses and glosses[0] != nil)       
-          sb+=("\t" + "suffix : " + glosses[0].gsub(";","/") + "\n")	       
+          sb+=("\tsuffix : #{glosses[0].gsub(";","/")}\n")	       
     end
     return sb
   end
@@ -603,32 +514,26 @@ class Solution
     end
     temp_POS = []
     arr.each do |pos|
-      array = pos.split("/");
+      array = pos.split("/")
       j=1
       if(type==1)
         sb = ""
       elsif(type==2)
-        sb = array[0] + "\t"
+        sb = "#{array[0]}\t"
       else
-        sb = LatinArabicTranslator.translate(array[0]) + "\t"
+        sb = "#{LatinArabicTranslator.translate(array[0])}\t"
         sb.force_encoding "UTF-8"
       end
-      while( j < array.length)
-        if (j > 1) 
-          sb+=" / "
-        end
-        sb+=array[j]
-        j+=1
-      end
+      sb <<  array[1..array.length].join(" / ")
       temp_POS.push(sb)
     end
     
     if(pre_stem_suff==2)
       if ((temp_POS.length > 1) and @debug) 
-        puts "More than one stem for " + temp_POS.to_s
+        puts "More than one stem for #{temp_POS.to_s}"
       end
       if (type ==1 and temp_POS[0].empty?) 
-        puts "Empty POS for stem " + get_stem_long_POS()
+        puts "Empty POS for stem #{get_stem_long_POS()}"
       end
       #return the first anyway :-(
       return temp_POS[0]	        
@@ -649,7 +554,7 @@ class Solution
     end
     if (temp_POS != nil)             			
               if (temp_POS[0]!=nil) 
-                sb+=("\t" + "prefix : " + temp_POS[0] + "\n")
+                sb << ("\tprefix : #{temp_POS[0]}\n")
               end	
     end
     if(arabic)
@@ -658,7 +563,7 @@ class Solution
       s = get_stem_long_POS()
     end
     if ( s != nil) 
-      sb+=("\t" + "stem : " + s + "\n")
+      sb << ("\tstem : #{s}  \n")
     end
     if(arabic)
       temp_POS =get_suffixes_arabic_long_POS()	
@@ -667,9 +572,21 @@ class Solution
     end
     if (temp_POS != nil)             		
               if (temp_POS[0]!=nil) 
-                sb+=("\t" + "suffix : " + temp_POS[0] + "\n")
+                sb << ("\tsuffix : #{temp_POS[0]}\n")
               end	
     end
     return sb
   end 
+  
 end
+
+class String
+  def ends_with_suffix_set?(ends_with_suffix_set) 
+      length = self.length
+      length.times { |i|
+	      return true if ends_with_suffix_set.member?(self[i..length])
+          
+	  } 
+    return false
+  end
+ end 

data/lib/raramorph/translator.rb

@@ -24,7 +24,7 @@ class Translator
   def translate(string)
          result = ""
          i = 0
-         ## IF non Utf8 Char REturn
+         ## IF non Utf8 Char return
          return string unless string.length % 2  ==0
          while i < string.length-1           
             char = string[i..i+1]

data/lib/raramorph.rb

@@ -1,8 +1,10 @@
 #Dir[File.join(File.dirname(__FILE__), 'raramorph/**/*.rb')].sort.each { |lib| require lib }
+
 $:.unshift File.expand_path(File.dirname(__FILE__) )
 start = Time.now
 require 'set'
-require 'stringio'
+require 'stringio'
+require 'raramorph/logger'
 require 'raramorph/translator'
 require 'raramorph/arabic_latin_translator'
 require 'raramorph/latin_arabic_translator'

data/lib/raramorph_main.rb

@@ -3,26 +3,31 @@
 # ARGV[2] # Verbose Default False
 # ARGV[4] # BuckWalter  Default False ( Arabic Output)
  $:.unshift File.expand_path(File.dirname(__FILE__) )
- if ARGV.length > 2 and ARGV.length <= 4 
+ if ARGV.length >= 2 and ARGV.length <= 4 
  require 'raramorph' 
  start = Time.now
- Raramorph.execute(ARGV[0] , ARGV[1] , ARGV[2] , ARGV[3] )
+ verbose = false
+ not_arabic = true
+ verbose = true  if ARGV[2] and ARGV[2] == "-v" 
+ not_arabic = false   if ARGV[3] and ARGV[3] == "-a" 
+ not_arabic = false if ARGV[2] and ARGV[2] == "-a"   
+ Raramorph.execute(ARGV[0] , ARGV[1] , verbose , not_arabic )
     puts "Time Elapsed= " + ( Time.now - start).to_s
  else
     puts("Arabic Morphological Analyzer for Ruby")
     puts("Ported to Ruby  by Moustafa Emara and Hany Salah El din , eSpace-technologies.(www.espace.com.eg) ,  2008.")
     puts("Based on :")
     puts("BUCKWALTER ARABIC MORPHOLOGICAL ANALYZER")
-    puts("This program is developed under the Ruby-Licences")
+    puts("This program is developed under the MIT-Licences")
     puts("Usage :")
     puts("")
-    puts("RaraMorph inFile [inEncoding] [outFile] [outEncoding] [-v]")
+    puts("raraMorph inFile [inEncoding] [outFile]  [-v] [-a]")
     puts("")
     puts("inFile : file to be analyzed")
     puts("inEncoding : encoding for inFile, default UTF-8")
-    puts("outFile : result file, default console")
-    puts("outEncoding : encoding for outFile, if not specified use Buckwalter transliteration with system's file.encoding")
+    puts("outFile : result file ")
     puts("-v : verbose mode")
+    puts("-a : Aarbic Output" )
  end
 
 

data/raramorph.gemspec

@@ -1,8 +1,8 @@
 Gem::Specification.new do |s|
   s.name     = "raramorph"
-  s.version  = "0.1.0"
+  s.version  = "0.1.1"
   s.date     = "2008-09-06"
-  s.summary  = "Raramorph is a ruby gem for making morphological analysis and arabic indexing built using Ruby at eSpace-technologies ( www.espace.com.eg )"
+  s.summary  = "Raramorph is a ruby gem for making morphological analysis and arabic indexing built using Ruby at eSpace-technologies ( www.espace.com.eg ) "
   s.email    = "moustafa.emara@espace.com.eg"
   s.homepage = "http://github.com/espace/raramorph"
   s.description = "Raramorph is a ruby gem for making morphological analysis and arabic indexing built using Ruby at eSpace-technologies ( www.espace.com.eg )"
@@ -20,6 +20,7 @@ Gem::Specification.new do |s|
 		"lib/raramorph/arabic_latin_translator.rb",
 		"lib/raramorph/latin_arabic_translator.rb",
 		"lib/raramorph/in_memory_dictionary_handler.rb",
+		"lib/raramorph/logger.rb",
 		"lib/dictionaries/dictPrefixes",
 		"lib/dictionaries/dictStems",
 		"lib/dictionaries/dictSuffixes",
@@ -34,7 +35,8 @@ Gem::Specification.new do |s|
   s.executables = %w(raramorph)
   s.required_ruby_version = '>= 1.9'
   s.bindir = "bin"
-  #s.rdoc_options = ["--main", "README"]
-  #s.extra_rdoc_files = ["README"]
+  s.rdoc_options = ["--main", "README"]
+  s.extra_rdoc_files = ["README"]
   #s.extensions << "ext/extconf.rb"
+
 end

metadata

@@ -3,7 +3,7 @@ rubygems_version: 0.9.4
 specification_version: 1
 name: raramorph
 version: !ruby/object:Gem::Version 
-  version: 0.1.0
+  version: 0.1.1
 date: 2008-09-06 00:00:00 +02:00
 summary: Raramorph is a ruby gem for making morphological analysis and arabic indexing built using Ruby at eSpace-technologies ( www.espace.com.eg )
 require_paths: 
@@ -39,6 +39,7 @@ files:
 - lib/raramorph/translator.rb
 - lib/raramorph/arabic_latin_translator.rb
 - lib/raramorph/latin_arabic_translator.rb
+- lib/raramorph/logger.rb
 - lib/dictionaries/dictPrefixes
 - lib/dictionaries/dictStems
 - lib/dictionaries/dictSuffixes
@@ -49,12 +50,14 @@ files:
 - lib/raramorph.rb
 - lib/raramorph_main.rb
 - lib/test_input/UTF-8.txt
+- README
 test_files: []
 
-rdoc_options: []
-
-extra_rdoc_files: []
-
+rdoc_options: 
+- --main
+- README
+extra_rdoc_files: 
+- README
 executables: 
 - raramorph
 extensions: []