facets 1.0.0 → 1.0.1

data/lib/facet/string/shuffle.rb

@@ -1,42 +0,0 @@
-require 'facet/array/shuffle'
-
-class String
-
-  # Return the string with seperated sections arranged
-  # in a random order. The default seperation is by character.
-  #
-  #   "Ruby rules".shuffle  #=> "e lybRsuur"
-  #
-  def shuffle(separator=//)
-    split(separator).shuffle.join('')
-  end
-
-  # In place version of shuffle.
-  #
-  def shuffle!(separator=//)
-    self.replace( shuffle(separator) )
-  end
-
-end
-
-
-#  _____         _
-# |_   _|__  ___| |_
-#   | |/ _ \/ __| __|
-#   | |  __/\__ \ |_
-#   |_|\___||___/\__|
-#
-=begin test
-
-  require 'test/unit'
-
-  class TCString < Test::Unit::TestCase
-
-    def test_shuffle
-      assert_nothing_raised { "abc 123".shuffle }
-      #assert_nothing_raised { "abc 123".shuffle! }
-    end
-
-  end
-
-=end

data/lib/facet/string/similarity.rb

@@ -1,108 +0,0 @@
-
-class String
-
-  # A fuzzy matching mechanism. Returns a score from 0-1,
-  # based on the number of shared edges.
-  # To be effective, the strings must be of length 2 or greater.
-  #
-  #   "Alexsander".fuzzy_match( "Aleksander" )  #=> 0.9
-  #
-  # The way it works:
-  #
-  # * Converts each string into a "graph like" object, with edges
-  #     "alexsander" -> [ alexsander, alexsand, alexsan ... lexsand ... san ... an, etc ]
-  #     "aleksander" -> [ aleksander, aleksand ... etc. ]
-  # * Perform match, then remove any subsets from this matched set (i.e. a hit
-  #   on "san" is a subset of a hit on "sander")
-  #     Above example, once reduced -> [ ale, sander ]
-  # * See's how many of the matches remain, and calculates a score based
-  #   on how many matches, their length, and compare to the length of the
-  #   larger of the two words.
-  #--
-  # Credit goes to Derek Lewis. Thanks Derek!
-  # Still a bit rough. Any suggestions for improvement are welcome.
-  #++
-  def similarity( str_in )
-    return 0 if str_in == nil
-    return 1 if self == str_in
-
-    # Make a graph of each word (okay, so its not a true graph, but is similar)
-    graph_A = Array.new
-    graph_B = Array.new
-
-    # "graph" self
-    last = self.length
-    (0..last).each do |ff|
-      loc  = self.length
-      break if ff == last - 1
-      wordB = (1..(last-1)).to_a.reverse!
-      if (wordB != nil)
-        wordB.each do |ss|
-          break if ss == ff
-          graph_A.push( "#{self[ff..ss]}" )
-        end
-      end
-    end
-
-    # "graph" input string
-    last = str_in.length
-    (0..last).each{ |ff|
-      loc  = str_in.length
-      break if ff == last - 1
-      wordB = (1..(last-1)).to_a.reverse!
-      wordB.each do |ss|
-        break if ss == ff
-        graph_B.push( "#{str_in[ff..ss]}" )
-      end
-    }
-
-
-    # count how many of these "graph edges" we have that are the same
-    matches = graph_A & graph_B
-    #matches = Array.new
-    #graph_A.each do |aa|
-    #  matches.push( aa ) if( graph_B.include?( aa ) )
-    #end
-
-    # For eliminating subsets, we want to start with the smallest hits.
-    matches.sort!{|x,y| x.length <=> y.length}
-
-    # eliminate any subsets
-    mclone = matches.dup
-    mclone.each_index do |ii|
-      reg = Regexp.compile( mclone[ii] )
-      count = 0.0
-      matches.each{|xx| count += 1 if xx =~ reg}
-      matches.delete(mclone[ii]) if count > 1
-    end
-
-    score = 0.0
-    matches.each{ |mm| score += mm.length }
-    self.length > str_in.length ? largest = self.length : largest = str_in.length
-    return score/largest
-  end
-
-  alias_method :fuzzy_match, :similarity
-
-end
-
-
-#  _____         _
-# |_   _|__  ___| |_
-#   | |/ _ \/ __| __|
-#   | |  __/\__ \ |_
-#   |_|\___||___/\__|
-#
-=begin test
-
-  require 'test/unit'
-
-  class TCString < Test::Unit::TestCase
-
-    def test_similarity
-      assert_nothing_raised { "Hello World!".similarity( "helo wrld" ) }
-    end
-
-  end
-
-=end

data/lib/facet/string/singular.rb

@@ -1,117 +0,0 @@
-
-class String
-
-  SINGULAR_RULES = [
-    [/(matr)ices$/i, '\1ix'],
-    [/(vert)ices$/i, '\1ex'],
-    [/^(ox)en/i, '\1'],
-    [/(alias)es$/i, '\1'],
-    [/([octop|vir])i$/i, '\1us'],
-    [/(cris|ax|test)es$/i, '\1is'],
-    [/(shoe)s$/i, '\1'],
-    [/(o)es$/i, '\1'],
-    [/(bus)es$/i, '\1'],
-    [/([m|l])ice$/i, '\1ouse'],
-    [/(x|ch|ss|sh)es$/i, '\1'],
-    [/(m)ovies$/i, '\1\2ovie'],
-    [/(s)eries$/i, '\1\2eries'],
-    [/([^aeiouy]|qu)ies$/i, '\1y'],
-    [/([lr])ves$/i, '\1f'],
-    [/(tive)s$/i, '\1'],
-    [/(hive)s$/i, '\1'],
-    [/([^f])ves$/i, '\1fe'],
-    [/(^analy)ses$/i, '\1sis'],
-    [/((a)naly|(b)a|(d)iagno|(p)arenthe|(p)rogno|(s)ynop|(t)he)ses$/i, '\1\2sis'],
-    [/([ti])a$/i, '\1um'],
-    [/(p)eople$/i, '\1\2erson'],
-    [/(m)en$/i, '\1an'],
-    [/(s)tatus$/i, '\1\2tatus'],
-    [/(c)hildren$/i, '\1\2hild'],
-    [/(n)ews$/i, '\1\2ews'],
-    [/s$/i, '']
-  ]
-
-  PLURAL_RULES = [
-    [/^(ox)$/i, '\1\2en'],                 # ox
-    [/([m|l])ouse$/i, '\1ice'],            # mouse, louse
-    [/(matr|vert)ix|ex$/i, '\1ices'],      # matrix, vertex, index
-    [/(x|ch|ss|sh)$/i, '\1es'],            # search, switch, fix, box, process, address
-    [/([^aeiouy]|qu)ies$/i, '\1y'],
-    [/([^aeiouy]|qu)y$/i, '\1ies'],        # query, ability, agency
-    [/(hive)$/i, '\1s'],                   # archive, hive
-    [/(?:([^f])fe|([lr])f)$/i, '\1\2ves'], # half, safe, wife
-    [/sis$/i, 'ses'],                      # basis, diagnosis
-    [/([ti])um$/i, '\1a'],                 # datum, medium
-    [/(p)erson$/i, '\1eople'],             # person, salesperson
-    [/(m)an$/i, '\1en'],                   # man, woman, spokesman
-    [/(c)hild$/i, '\1hildren'],            # child
-    [/(buffal|tomat|potat)o$/i, '\1\2oes'],      # buffalo, tomato
-    [/(bu)s$/i, '\1\2ses'],                # bus
-    [/(alias)/i, '\1es'],                  # alias
-    [/(octop|vir)us$/i, '\1i'],            # octopus, virus - virus has no defined plural, but viri is better than viruses/viruss
-    [/(ax|cri|test)is$/i, '\1es'],         # axis, crisis  
-    [/s$/i, 's'],                          # no change (compatibility)
-    [/$/, 's']
-  ]
-
-
-  # Convert an English word from plurel to singular.
-  #
-  #   "boys".singular      #=> boy
-  #   "tomatoes".singular  #=> tomato
-  #
-  def singular
-    result = self.to_s.dup
-    String::SINGULAR_RULES.each do |(rule, replacement)|
-      break if result.gsub!(rule, replacement)
-    end
-    return result
-  end
-
-  # Convert an English word from singular to plurel.
-  #
-  #   "boy".plural     #=> boys
-  #   "tomato".plural  #=> tomatoes
-  #
-  def plural
-    result = self.to_s.dup
-    String::PLURAL_RULES.each do |(rule, replacement)|
-      break if result.gsub!(rule, replacement)
-    end
-    return result
-  end
-
-  # Deprecated alias for #singular.
-  alias_method( :singularize, :singular )
-
-  # Deprecated alias for #plural.
-  alias_method( :pluralize, :plural )
-
-end
-
-
-#  _____         _
-# |_   _|__  ___| |_
-#   | |/ _ \/ __| __|
-#   | |  __/\__ \ |_
-#   |_|\___||___/\__|
-#
-=begin test
-
-  require 'test/unit'
-
-  class TCString < Test::Unit::TestCase
-
-    def test_singular
-      assert_equal( "friend", "friends".singular )
-      assert_equal( "man", "men".singular )    
-    end
-
-    def test_plural
-      assert_equal( "friends", "friend".plural )
-      assert_equal( "men", "man".plural )
-    end
-
-  end
-
-=end

data/lib/facet/string/slap.rb

@@ -1,44 +0,0 @@
-
-class String
-
-  # Like push but works from the other end of the string.
-  def slap( str=' ' )
-    insert(0, str)
-  end
-
-end
-
-
-#  _____         _
-# |_   _|__  ___| |_
-#   | |/ _ \/ __| __|
-#   | |  __/\__ \ |_
-#   |_|\___||___/\__|
-#
-=begin test
-
-  require 'test/unit'
-
-  class TCString < Test::Unit::TestCase
-
-    def setup
-      @a =  ""
-    end
-
-    def test_001
-      #assert_raises( ArgumentError ) { @a.slap }
-      assert_raises( ArgumentError ) { @a.slap(1,2) }
-    end
-
-    def test_002
-      assert_equal( "0", @a.slap("0") )
-      assert_equal( "10", @a.slap("1") )
-      assert_equal( "210", @a.slap("2") )
-      assert_equal( "3210", @a.slap("3") )
-      assert_equal( "43210", @a.slap("4") )
-      assert_equal( "543210", @a.slap("5") )
-    end
-
-  end
-
-=end

data/lib/facet/string/soundex.rb

@@ -1,102 +0,0 @@
-
-class String
-
-  # Implementation of the soundex algorithm as described by Knuth
-  # in volume 3 of The Art of Computer Programming. Returns nil
-  # if the value couldn't be calculated b/c of empty-string or
-  # invalid character.
-  #
-  #   "Ruby".soundex  #=> "R100"
-  #
-  #--
-  # Credit goes to Michael Neumann (neumann@s-direktnet.de).
-  #++
-  def soundex
-    return nil if self.empty?
-
-    str = self.upcase
-    last_code = String.soundex_code(str[0,1])
-    soundex_code = str[0,1]
-
-    for index in 1...(str.size) do
-      return soundex_code if soundex_code.size == 4
-
-      code = String.soundex_code(str[index,1])
-
-      if code == "0" then
-        last_code = nil
-      elsif code == nil then
-        return nil
-      elsif code != last_code then
-        soundex_code += code
-        last_code = code
-      end
-    end
-
-    return soundex_code + "000"[0,4-soundex_code.size]
-  end
-
-  # Support function for String#soundex. Returns code for a single character.
-  def String.soundex_code(character)
-    character.tr! "AEIOUYWHBPFVCSKGJQXZDTLMNR", "00000000111122222222334556"
-  end
-
-end
-
-
-#  _____         _
-# |_   _|__  ___| |_
-#   | |/ _ \/ __| __|
-#   | |  __/\__ \ |_
-#   |_|\___||___/\__|
-#
-=begin test
-
-  require 'test/unit'
-
-  class TCString < Test::Unit::TestCase
-
-    def test_soundex
-      assert_equal("Ruby".soundex, "R100")
-    end
-
-  end
-
-  class TC_Soundex < Test::Unit::TestCase
-
-    TESTVEC = "Euler Ellery Gauss Ghosh Hilbert Heilbronn Knuth Kant Lloyd Ladd Lukasiewicz Lissajous".split(" ")
-    RESVEC  = "E460 E460 G200 G200 H416 H416 K530 K530 L300 L300 L222 L222".split(" ")
-
-    def test_soundex
-      TESTVEC.each_with_index {|str,i| 
-        res = str.soundex
-        #print "#{str.ljust(11)} => #{res} ... "
-        assert_equal( RESVEC[i], res )
-      }
-    end
-
-  end
-
-=end
-
-
-# if __FILE__ == $0
-#   testvec = "Euler Ellery Gauss Ghosh Hilbert Heilbronn Knuth Kant Lloyd Ladd Lukasiewicz Lissajous".split(" ")
-#   resvec  = "E460 E460 G200 G200 H416 H416 K530 K530 L300 L300 L222 L222".split(" ")
-#    
-#   wrong = 0
-#   
-#   testvec.each_with_index {|str,i|
-#     res = str.soundex
-#     print "#{str.ljust(11)} => #{res} ... "
-#     if res == resvec[i] then
-#       puts "ok"
-#     else
-#       wrong += 1
-#       puts "failed, had to be #{resvec[i]}"
-#     end
-#   }
-#   puts "summary: #{wrong} of #{testvec.size} tests failed!"
-#   readline
-# end
-

data/lib/facet/string/starts_with.rb

@@ -1,24 +0,0 @@
-#--
-# Credit goes to  Lucas Carlson and Blaine Cook.
-#++
-
-class String
-
-  def starts_with?(str)
-    self.index( str ) == 0
-  end
-
-  def ends_with?(str)
-    self.rindex( str ) == self.length - str.length
-  end
-
-end
-
-
-#  _____         _
-# |_   _|__  ___| |_
-#   | |/ _ \/ __| __|
-#   | |  __/\__ \ |_
-#   |_|\___||___/\__|
-#
-# TODO

data/lib/facet/string/succ.rb

@@ -1,38 +0,0 @@
-class String
-  alias_method( :succ_once, :succ )
-  # Allows #succ to take _n_ step increments.
-  #
-  #   "abc".succ      #=> "abd"
-  #   "abc".succ(4)   #=> "abg"
-  #   "abc".succ(24)  #=> "aca"
-  #
-  def succ(n=1)
-    s = self
-    n.times { s = s.succ_once }
-    s
-  end
-end
-
-
-#  _____         _
-# |_   _|__  ___| |_
-#   | |/ _ \/ __| __|
-#   | |  __/\__ \ |_
-#   |_|\___||___/\__|
-#
-=begin test
-
-  require 'test/unit'
-
-  class TCString < Test::Unit::TestCase
-
-    def test_succ
-      assert_equal( "b", "a".succ )
-      assert_equal( "b", "a".succ(1) )
-      assert_equal( "c", "a".succ(2) )
-      assert_equal( "d", "a".succ(3) )
-    end
-
-  end
-
-=end