tinycus 1.0.9 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f72c3f525833a5d89fb848a6420279f4844dc415ceca2cfc7175386f3e2dd937
-  data.tar.gz: aecc63197fc8b456d72d5fad485abb9aa196dcfae4cc12b518dcaaf73c6ab180
+  metadata.gz: 6c1eec898c95abe9a16e91e709d5727d320c7a797764e34687092225eb3ca19a
+  data.tar.gz: ded9cefb4a86639b89fdf0c39ab0751892b6722b9f4a2920450571a209eb5cbb
 SHA512:
-  metadata.gz: b144d74a8fae7aa860d5eb5f8edaf70fa54af93a08c6a1859c137a16095db0c7d906edc7c9fd121617d1cf312fa948fd4f42c1730b7014e8cb603ec774477411
-  data.tar.gz: 440fda68bf56748e308f59bf660366ec2e2439b6f09540a8c4aa772b982083442ba2fe42c6b73ba2d71968903b17320ea62dcaeb18471aeb47c1d63f72dab6a8
+  metadata.gz: 44a433108259fd71617245eb974043df5f58753fd565373108b2e5cc23ae8b3ebade1853ab1fc4ce021fe05ee0b3f94e514b949bc5f04cfe587c2c804b83119d
+  data.tar.gz: 67edff394d6cea2d25e098d6b86a42cfe9b794342605873c71abb7c61696d7f71a693cd5044e131045a57568201aac7544961002203efaa6996c0aa0216922f3

data/tinycus.rb

@@ -26,7 +26,7 @@ The four "alpha_" functions work on Greek and English, also most Latin character
   end
 
   def Tinycus.alpha_collation() # :nodoc:
-    return Tinycus::Tr.get_greek_collation_tr
+    return Tinycus.get_tr('greek_to_collation_form')
   end
 
   # synonym of Tinycus.contains_vowel, for readability when using it on a single character
@@ -212,25 +212,11 @@ The four "alpha_" functions work on Greek and English, also most Latin character
       forms = forms+forms.map { |x| x.capitalize }
       return forms.uniq
     end
+
   end
 
   class Tinycus::Tr
 
-    @@prep_remove_acute_and_grave_from_greek = nil
-    @@prep_remove_circumflex_from_greek = nil
-    @@prep_add_circumflex_to_greek = nil
-    @@prep_remove_grave_from_greek = nil
-    @@prep_remove_acute_from_greek = nil
-    @@prep_add_grave_to_greek = nil
-    @@prep_add_acute_to_greek = nil
-    @@prep_remove_diar_from_greek = nil
-    @@prep_remove_breathing_from_greek = nil
-    @@prep_add_diar_to_greek = nil
-    @@prep_remove_accents_from_greek = nil
-    @@greek_grave_to_acute = nil
-    @@greek_acute_to_grave = nil
-    @@prep_greek_to_collation_form = nil
-
     # Initialize a data structure that represents an action equivalent to String#tr(a,b), but faster.
     # Including redundant characters or unchanged characters is harmless and is fixed in this constructor; it does not cause
     # any performance hit when the object is actually used. The initializer takes linear time and memory in the size of
@@ -289,160 +275,27 @@ The four "alpha_" functions work on Greek and English, also most Latin character
       end
     end
 
-    def Tr.greek_grave_to_acute(s,n:false)
-      if @@greek_grave_to_acute.nil? then
-        @@greek_grave_to_acute = Tinycus::Tr.new(
-          "ÀÈÌÒÙàèìòùἂἃἊἒἓἢἣἫἲἳὂὃὊὋὓὢὣὫὰὲὴὶὸὺὼῒῢῸῂ","ÁÉÍÓÚáéíóúἄἅἌἔἕἤἥἭἴἵὄὅὌὍὕὤὥὭάέήίόύώΐΰΌῄ"
-        )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@greek_grave_to_acute.apply(s)
-    end
-
-    def Tr.greek_acute_to_grave(s,n:false)
-      if @@greek_acute_to_grave.nil? then
-        @@greek_acute_to_grave = Tinycus::Tr.new(
-          "ÁÉÍÓÚáéíóúἄἅἌἔἕἤἥἭἴἵὄὅὌὍὕὤὥὭάέήίόύώΐΰΌ","ÀÈÌÒÙàèìòùἂἃἊἒἓἢἣἫἲἳὂὃὊὋὓὢὣὫὰὲὴὶὸὺὼῒῢῸ"
-        )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@greek_acute_to_grave.apply(s)
-    end
-
-    def Tr.remove_tonal_accents_from_greek(s,n:false)
-      # to do: make this more efficient by creating a single-pass tr
-      return Tr.remove_circumflex_from_greek(Tr.remove_acute_and_grave_from_greek(s,n:n))
-    end
-
-    def Tr.remove_acute_and_grave_from_greek(s,n:false)
-      if @@prep_remove_acute_and_grave_from_greek.nil? then
-        @@prep_remove_acute_and_grave_from_greek =       
-            Tinycus::Tr.new(
-              "ÀÁàáÈÉèéÌÍìíÒÓòóÙÚùúÝýΆάἂἃἄἅἊἌἍὰᾴΈέἒἓἔἕἜἝὲήἢἣἤἥἫἬἭὴᾓᾔᾕῂῄΊΐίἲἳἴἵἼἽὶῒΌόὂὃὄὅὊὋὌὍὸῸΰύὓὔὕὝὺῢώὢὣὤὥὫὬὭὼᾤῴᾍ",
-              "AAaaEEeeIIiiOOooUUuuYyΑαἀἁἀἁἈἈἉαᾳΕεἐἑἐἑἘἙεηἠἡἠἡἩἨἩηᾑᾐᾑῃῃΙϊιἰἱἰἱἸἹιϊΟοὀὁὀὁὈὉὈὉοΟϋυὑὐὑὙυϋωὠὡὠὡὩὨὩωᾠῳᾉ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_remove_acute_and_grave_from_greek.apply(s)
-    end
-
-    def Tr.remove_circumflex_from_greek(s,n:false)
-      if @@prep_remove_circumflex_from_greek.nil? then
-        @@prep_remove_circumflex_from_greek =       
-            Tinycus::Tr.new(
-              "ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÑÒÓÔÕÖØÙÚÛÜÝàáâãäåæçèéêëìíîïñòóôõöøùúûüýÿΆΈΊΌΐάέήίΰϊϋόύώỏἀἁἂἃἄἅἆἈἉἊἌἍἎἐἑἒἓἔἕἘἙἜἝἠἡἢἣἤἥἦἧἨἩἫἬἭἮἯἰἱἲἳἴἵἶἷἸἹἼἽἾὀὁὂὃὄὅὈὉὊὋὌὍὐὑὓὔὕὖὗὙὝὠὡὢὣὤὥὦὧὨὩὫὬὭὮὯὰὲὴὶὸὺὼᾐᾑᾓᾔᾕᾖᾗᾠᾤᾦᾧᾰᾱᾳᾴᾶᾷᾸᾹῂῃῄῆῇῐῑῒῖῗῘῙῠῡῢῥῦῨῩῬῳῴῶῷῸ",
-              "ÀÁAAÄÅÆÇÈÉEËÌÍIÏNÒÓOOÖØÙÚUÜÝàáaaäåæçèéeëìíiïnòóooöøùúuüýÿΆΈΊΌΐάέήίΰϊϋόύώỏἀἁἂἃἄἅἀἈἉἊἌἍἈἐἑἒἓἔἕἘἙἜἝἠἡἢἣἤἥἠἡἨἩἫἬἭἨἩἰἱἲἳἴἵἰἱἸἹἼἽἸὀὁὂὃὄὅὈὉὊὋὌὍὐὑὓὔὕὐὑὙὝὠὡὢὣὤὥὠὡὨὩὫὬὭὨὩὰὲὴὶὸὺὼᾐᾑᾓᾔᾕᾐᾑᾠᾤᾠᾡᾰᾱᾳᾴαᾳᾸᾹῂῃῄηῃῐῑῒιϊῘῙῠῡῢῥυῨῩῬῳῴωῳῸ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_remove_circumflex_from_greek.apply(s)
-    end
-
-    def Tr.add_circumflex_to_greek(s,n:false)
-      if @@prep_add_circumflex_to_greek.nil? then
-        @@prep_add_circumflex_to_greek =       
-            Tinycus::Tr.new(
-              "AAEINOOUaaeinoouἀἈἠἡἨἩἰἱἸὐὑὠὡὨὩᾐᾑᾠᾡαᾳηῃιϊυωῳ",
-              "ÂÃÊÎÑÔÕÛâãêîñôõûἆἎἦἧἮἯἶἷἾὖὗὦὧὮὯᾖᾗᾦᾧᾶᾷῆῇῖῗῦῶῷ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_add_circumflex_to_greek.apply(s)
-    end
+    def Tr.add_acute_to_greek(s,n:false)          return Tinycus.get_tr('add_acute_to_greek').apply(s,n:n)    end
+    def Tr.add_circumflex_to_greek(s,n:false)     return Tinycus.get_tr('add_circumflex_to_greek').apply(s,n:n)    end
+    def Tr.add_grave_to_greek(s,n:false)          return Tinycus.get_tr('add_grave_to_greek').apply(s,n:n)    end
 
-    def Tr.remove_acute_from_greek(s,n:false)
-      if @@prep_remove_acute_from_greek.nil? then
-        @@prep_remove_acute_from_greek =       
-            Tinycus::Tr.new(
-              "ÁÉÍÓÚáéíóúἄἅἌἔἕἤἥἭἴἵὄὅὌὍὕὤὥὭάέήίόύώῄῴΐΰΌ",
-              "AEIOUaeiouἀἁἈἐἑἠἡἩἰἱὀὁὈὉὑὠὡὩαεηιουωῃῳϊϋΟ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_remove_acute_from_greek.apply(s)
-    end
+    def Tr.remove_acute_from_greek(s,n:false)     return Tinycus.get_tr('remove_acute_from_greek').apply(s,n:n)    end
+    def Tr.remove_grave_from_greek(s,n:false)     return Tinycus.get_tr('remove_grave_from_greek').apply(s,n:n)    end
+    def Tr.remove_circumflex_from_greek(s,n:false)      return Tinycus.get_tr('remove_circumflex_from_greek').apply(s,n:n)    end
+    def Tr.remove_tonal_accents_from_greek(s,n:false)   return Tinycus.get_tr('remove_tonal_accents_from_greek').apply(s,n:n)    end
+    def Tr.remove_acute_and_grave_from_greek(s,n:false) return Tinycus.get_tr('remove_acute_and_grave_from_greek').apply(s,n:n)    end
 
-    def Tr.remove_grave_from_greek(s,n:false)
-      if @@prep_remove_grave_from_greek.nil? then
-        @@prep_remove_grave_from_greek =       
-            Tinycus::Tr.new(
-              "ÀÈÌÒÙàèìòùἂἃἊἒἓἢἣἫἲἳὂὃὊὋὓὢὣὫὰὲὴὶὸὺὼῂῒῢῸ",
-              "AEIOUaeiouἀἁἈἐἑἠἡἩἰἱὀὁὈὉὑὠὡὩαεηιουωῃϊϋΟ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_remove_grave_from_greek.apply(s)
-    end
+    def Tr.greek_grave_to_acute(s,n:false)              return Tinycus.get_tr('greek_grave_to_acute').apply(s,n:n)    end
+    def Tr.greek_acute_to_grave(s,n:false)              return Tinycus.get_tr('greek_acute_to_grave').apply(s,n:n)    end
 
-    def Tr.add_grave_to_greek(s,n:false)
-      if @@prep_add_grave_to_greek.nil? then
-        @@prep_add_grave_to_greek =       
-            Tinycus::Tr.new(
-              "AEIOUaeiouἀἁἈἐἑἠἡἩἰἱὀὁὈὉὑὠὡὩαεηιουωῃϊϋΟ",
-              "ÀÈÌÒÙàèìòùἂἃἊἒἓἢἣἫἲἳὂὃὊὋὓὢὣὫὰὲὴὶὸὺὼῂῒῢῸ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_add_grave_to_greek.apply(s)
-    end
+    def Tr.add_diar_to_greek(s,n:false)           return Tinycus.get_tr('add_diar_to_greek').apply(s,n:n)    end
+    def Tr.remove_diar_from_greek(s,n:false)      return Tinycus.get_tr('remove_diar_from_greek').apply(s,n:n)    end
 
-    def Tr.add_acute_to_greek(s,n:false)
-      if @@prep_add_acute_to_greek.nil? then
-        @@prep_add_acute_to_greek =       
-            Tinycus::Tr.new(
-              "AEIOUaeiouἀἁἈἐἑἠἡἩἰἱὀὁὈὉὑὠὡὩαεηιουωῃῳϊϋΟ",
-              "ÁÉÍÓÚáéíóúἄἅἌἔἕἤἥἭἴἵὄὅὌὍὕὤὥὭάέήίόύώῄῴΐΰΌ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_add_acute_to_greek.apply(s)
-    end
+    def Tr.remove_breathing_from_greek(s,n:false) return Tinycus.get_tr('remove_breathing_from_greek').apply(s,n:n)    end
 
-    def Tr.remove_diar_from_greek(s,n:false)
-      # Can't do caps with diaresis, since they only exist as combining characters.
-      if @@prep_remove_diar_from_greek.nil? then
-        @@prep_remove_diar_from_greek =       
-            Tinycus::Tr.new(
-              "ϊΐῒῗϋΰῢ",
-              "ιίὶῖυύὺ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_remove_diar_from_greek.apply(s)
-    end
+    def Tr.remove_accents_from_greek(s,n:false)   return Tinycus.get_tr('remove_accents_from_greek').apply(s,n:n)    end
+    def Tr.greek_to_collation_form(s,n:false)     return Tinycus.get_tr('greek_to_collation_form').apply(s,n:n)    end
 
-    def Tr.add_diar_to_greek(s,n:false)
-      # Can't do caps with diaresis, since they only exist as combining characters.
-      if @@prep_add_diar_to_greek.nil? then
-        @@prep_add_diar_to_greek =       
-            Tinycus::Tr.new(
-              "ιίὶῖυύὺ",
-              "ϊΐῒῗϋΰῢ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_add_diar_to_greek.apply(s)
-    end
-
-    def Tr.remove_breathing_from_greek(s,n:false)
-      if @@prep_remove_breathing_from_greek.nil? then
-        @@prep_remove_breathing_from_greek =       
-            Tinycus::Tr.new(
-              "ἄἌἈἈἀἈἁἉἂἊἅἍἆἉἉἃἋᾇἔἜἑἙἐἘἕἝἘἘἙἙἓἛἒἚἣἫἡἩἠἨἦἥἭἢἪἤἬᾔἬΙἧᾗἨἨᾕἭΙἩἩᾐἨΙᾖᾑἩΙἰἸἱἹἴἼἶἳἻἵἽἷἸἸἲἺἹἹὃὋὄὌὀὈὈὈὅὍὁὉὉὉῥῬῬῬῤὐὗὕὝὑὙὖὔὓὛὙὙὥὭὣὫὤὬᾤὬΙὠὨὦᾧὡὩὧᾠὨΙὨὨὢὪᾦὩὩ",
-              "άΆΑΑαΑαΑὰᾺάΆᾶΑΑὰᾺᾷέΈεΕεΕέΈΕΕΕΕὲῈὲῈὴῊηΗηΗῆήΉὴῊήΉῄΉΙῆῇΗΗῄΉΙΗΗῃΗΙῇῃΗΙιΙιΙίΊῖὶῚίΊῖΙΙὶῚΙΙὸῸόΌοΟΟΟόΌοΟΟΟρΡΡΡρυῦύΎυΥῦύὺῪΥΥώΏὼῺώΏῴΏΙωΩῶῷωΩῶῳΩΙΩΩὼῺῷΩΩ"
-            )
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_remove_breathing_from_greek.apply(s)
-    end
-
-    def Tr.remove_accents_from_greek(s,n:false)
-      if @@prep_remove_accents_from_greek.nil? then
-        @@prep_remove_accents_from_greek = Tr.remove_accents('el')
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_remove_accents_from_greek.apply(s)
-    end
 
     # Slow.
     def Tr.remove_macrons_and_breves(s)
@@ -544,21 +397,6 @@ print a.join('|'),"--\n"
 =end
     end
 
-    def Tr.get_greek_collation_tr # :nodoc:
-      if @@prep_greek_to_collation_form.nil? then
-        @@prep_greek_to_collation_form = Tr.collation_form('el')
-      end
-      return @@prep_greek_to_collation_form
-    end
-
-    def Tr.greek_to_collation_form(s,n:false)
-      if @@prep_greek_to_collation_form.nil? then
-        @@prep_greek_to_collation_form = Tr.collation_form('el')
-      end
-      if n then s=s.unicode_normalize(:nfc) end
-      return @@prep_greek_to_collation_form.apply(s)
-    end
-
     # Returns a Tinycus::Tr object which can then be used to act on strings using the apply() method.
     # The 'el' locale is a standard thing that software like ICU uses for polytonic Greek. The object constructed with this
     # locale will also remove most accents and macrons from Latin characters, but will miss some cases like Czech, and will not handle Cyrillic.
@@ -884,6 +722,8 @@ def Util.canonicalize_greek_word(w,n:false)
   # Works on a single word, not an entire string.
   # Is designed so that calling it on a Latin word is fast and harmless.
   # The n argument has the same definition as in Tinycus::Tr.remove_accents_from_greek().
+  # To do this on an IfMows object, use IfMows#canonicalize. Converting from string to IfMows, canonicalizing, and then going back to string
+  # is about 10 times slower than this function.
   if !looks_greek(w) then return w end # is fast on Latin script
   if n then w = w.unicode_normalize(:nfc) end
   w = to_single_accent(w)
@@ -1073,6 +913,71 @@ JSON
     return b
   end
 
+  #------------------------------------------------------------------------------------------------
+  # Build tr table the first time the relevant function is called.
+  #------------------------------------------------------------------------------------------------
+  @@greek_tr_tables = {}
+  def Tinycus.get_tr(function_name) # :nodoc:
+    if @@greek_tr_tables.has_key?(function_name) then return @@greek_tr_tables[function_name] end
+    operations = {
+      'add_acute_to_greek'=>       {'add_tonal'=>'acute'},
+      'add_circumflex_to_greek'=>  {'add_tonal'=>'circumflex'},
+      'add_grave_to_greek'=>       {'add_tonal'=>'grave'},
+
+      'remove_acute_from_greek'=>          {'remove_tonal'=>['acute']},
+      'remove_circumflex_from_greek'=>     {'remove_tonal'=>['circumflex']},
+      'remove_grave_from_greek'=>          {'remove_tonal'=>['grave']},
+      'remove_tonal_accents_from_greek'=>  {'remove_tonal'=>['acute','circumflex','grave']},
+      'remove_acute_and_grave_from_greek'=>{'remove_tonal'=>['acute','grave']},
+
+      'greek_acute_to_grave'=>             {'change_tonal'=>['acute','grave']},
+      'greek_grave_to_acute'=>             {'change_tonal'=>['grave','acute']},
+
+      # Can't do caps with diaresis, since they only exist as combining characters.
+      'add_diar_to_greek'=>                {'add_boolean'=>['diar'],'lc_only'=>true},
+      'remove_diar_from_greek'=>           {'remove_boolean'=>['diar'],'lc_only'=>true},
+
+      'remove_breathing_from_greek'=>      {'set_string'=>['breathing','none']},
+
+      'remove_accents_from_greek'=>        {'set_string'=>['breathing','none'],
+                                            'remove_boolean'=>['diar','iota_subscript'],
+                                            'remove_tonal'=>['acute','circumflex','grave']},
+      'greek_to_collation_form'=>          {'set_string'=>['breathing','none'],
+                                            'remove_boolean'=>['diar','iota_subscript','uppercase'],
+                                            'remove_tonal'=>['acute','circumflex','grave']},
+    }[function_name]
+    if operations.nil? then raise "undefined tr function #{function_name}" end
+    a = ''
+    b = ''
+    Tinycus.all_greek_characters.chars.each { |c|
+      next if operations['lc_only'] && c!=c.downcase
+      plain,d = Tinycus.disassemble_greek_char(c)
+      if operations.has_key?('add_tonal') then d['tonal']=operations['add_tonal'] end
+      if operations.has_key?('remove_tonal') then
+        operations['remove_tonal'].each { |acc| if d['tonal']==acc then d['tonal']='none' end }
+      end
+      if operations.has_key?('change_tonal') then
+        from,to = operations['change_tonal']
+        if d['tonal']==from then d['tonal']=to end
+      end
+      if operations.has_key?('add_boolean') then
+        operations['add_boolean'].each { |x|
+          unless c!=c.downcase && x=='diar' then d[x]=true end # Can't do caps with diaresis, since they only exist as combining characters.
+        }
+      end
+      if operations.has_key?('remove_boolean') then operations['remove_boolean'].each { |x| d[x]=false } end
+      if operations.has_key?('set_string') then x,y=operations['set_string']; d[x]=y end
+      c2 = Tinycus.assemble_greek_char(plain,d)
+      next if c2.nil? # happens for stuff like uppercase alpha with smooth breathing and acute
+      # if c2.nil? then raise "unable to assemble #{plain} #{d}, should have had key present as #{plain}#{Tinycus.assemble_greek_char_d_to_hex(plain,d)}" end
+      next if c2==c
+      a += c
+      b += c2
+    }
+    @@greek_tr_tables[function_name] = Tinycus::Tr.new(a,b)
+    return @@greek_tr_tables[function_name]
+  end
+
   # Returns [plain,d], where plain is a lowercase, unaccented Greek letter (α-ω, plus ς), and d is
   # a hash with the following keys:
   #   uppercase, diar, iota_subscript - boolean values
@@ -1100,8 +1005,7 @@ JSON
     return [plain,d]
   end
 
-  # The inverse of Tinycus.disassemble_greek_char.
-  def Tinycus.assemble_greek_char(plain,d)
+  def Tinycus.assemble_greek_char_d_to_hex(plain,d)
     b = 0
     b |=        0b1 if d['uppercase']
     b |=       0b10 if d['diar']
@@ -1111,7 +1015,12 @@ JSON
     b |=    0b11000 if d['tonal']=='circumflex'
     b |=  0b0100000 if d['breathing']=='smooth'
     b |=  0b1000000 if d['breathing']=='rough'
-    x = plain+("%.2x" % b)
+    return ("%.2x" % b)
+  end
+
+  # The inverse of Tinycus.disassemble_greek_char.
+  def Tinycus.assemble_greek_char(plain,d)
+    x = plain+Tinycus.assemble_greek_char_d_to_hex(plain,d)
     return Tinycus.assemble_greek_char_hex(x)
   end
 
@@ -1136,17 +1045,35 @@ JSON
     return @@assemble_greek_char_hash[x]
   end
 
+  @@all_greek_characters = nil
+
+  def Tinycus.all_greek_characters
+    # Returns a string containing all the characters of the Greek alphabet, including all accentuations, in the standardized forms
+    # that are allowed by Tinycus.
+    if @@all_greek_characters.nil? then
+      @@all_greek_characters = @@disassemble_greek_char_hash.keys.join
+    end
+    return @@all_greek_characters
+  end
+
+
 # The following are output by generating/assemble_disassemble.rb .
 @@disassemble_greek_char_hash = {
   'α'=>['α',0b0],
   'Α'=>['α',0b1],
   'ᾳ'=>['α',0b100],
   'ά'=>['α',0b1000],
+  'Ά'=>['α',0b1001],
+  'ᾴ'=>['α',0b1100],
   'ὰ'=>['α',0b10000],
+  'Ὰ'=>['α',0b10001],
+  'ᾲ'=>['α',0b10100],
   'ᾶ'=>['α',0b11000],
   'ᾷ'=>['α',0b11100],
   'ἀ'=>['α',0b100000],
   'Ἀ'=>['α',0b100001],
+  'ᾀ'=>['α',0b100100],
+  'ᾈ'=>['α',0b100101],
   'ἄ'=>['α',0b101000],
   'Ἄ'=>['α',0b101001],
   'ᾄ'=>['α',0b101100],
@@ -1156,10 +1083,14 @@ JSON
   'Ἆ'=>['α',0b111001],
   'ἁ'=>['α',0b1000000],
   'Ἁ'=>['α',0b1000001],
+  'ᾁ'=>['α',0b1000100],
+  'ᾉ'=>['α',0b1000101],
   'ἅ'=>['α',0b1001000],
   'Ἅ'=>['α',0b1001001],
   'ᾅ'=>['α',0b1001100],
+  'ᾍ'=>['α',0b1001101],
   'ἃ'=>['α',0b1010000],
+  'Ἃ'=>['α',0b1010001],
   'ᾇ'=>['α',0b1011100],
   'β'=>['β',0b0],
   'Β'=>['β',0b1],
@@ -1170,25 +1101,31 @@ JSON
   'ε'=>['ε',0b0],
   'Ε'=>['ε',0b1],
   'έ'=>['ε',0b1000],
+  'Έ'=>['ε',0b1001],
   'ὲ'=>['ε',0b10000],
+  'Ὲ'=>['ε',0b10001],
   'ἐ'=>['ε',0b100000],
   'Ἐ'=>['ε',0b100001],
   'ἔ'=>['ε',0b101000],
   'Ἔ'=>['ε',0b101001],
   'ἒ'=>['ε',0b110000],
+  'Ἒ'=>['ε',0b110001],
   'ἑ'=>['ε',0b1000000],
   'Ἑ'=>['ε',0b1000001],
   'ἕ'=>['ε',0b1001000],
   'Ἕ'=>['ε',0b1001001],
   'ἓ'=>['ε',0b1010000],
+  'Ἓ'=>['ε',0b1010001],
   'ζ'=>['ζ',0b0],
   'Ζ'=>['ζ',0b1],
   'η'=>['η',0b0],
   'Η'=>['η',0b1],
   'ῃ'=>['η',0b100],
   'ή'=>['η',0b1000],
+  'Ή'=>['η',0b1001],
   'ῄ'=>['η',0b1100],
   'ὴ'=>['η',0b10000],
+  'Ὴ'=>['η',0b10001],
   'ῂ'=>['η',0b10100],
   'ῆ'=>['η',0b11000],
   'ῇ'=>['η',0b11100],
@@ -1199,6 +1136,7 @@ JSON
   'Ἤ'=>['η',0b101001],
   'ᾔ'=>['η',0b101100],
   'ἢ'=>['η',0b110000],
+  'Ἢ'=>['η',0b110001],
   'ἦ'=>['η',0b111000],
   'Ἦ'=>['η',0b111001],
   'ᾖ'=>['η',0b111100],
@@ -1210,6 +1148,7 @@ JSON
   'ᾕ'=>['η',0b1001100],
   'ἣ'=>['η',0b1010000],
   'Ἣ'=>['η',0b1010001],
+  'ᾓ'=>['η',0b1010100],
   'ἧ'=>['η',0b1011000],
   'Ἧ'=>['η',0b1011001],
   'ᾗ'=>['η',0b1011100],
@@ -1218,9 +1157,12 @@ JSON
   'ι'=>['ι',0b0],
   'Ι'=>['ι',0b1],
   'ϊ'=>['ι',0b10],
+  'Ϊ'=>['ι',0b11],
   'ί'=>['ι',0b1000],
+  'Ί'=>['ι',0b1001],
   'ΐ'=>['ι',0b1010],
   'ὶ'=>['ι',0b10000],
+  'Ὶ'=>['ι',0b10001],
   'ῒ'=>['ι',0b10010],
   'ῖ'=>['ι',0b11000],
   'ῗ'=>['ι',0b11010],
@@ -1229,6 +1171,7 @@ JSON
   'ἴ'=>['ι',0b101000],
   'Ἴ'=>['ι',0b101001],
   'ἲ'=>['ι',0b110000],
+  'Ἲ'=>['ι',0b110001],
   'ἶ'=>['ι',0b111000],
   'Ἶ'=>['ι',0b111001],
   'ἱ'=>['ι',0b1000000],
@@ -1236,7 +1179,9 @@ JSON
   'ἵ'=>['ι',0b1001000],
   'Ἵ'=>['ι',0b1001001],
   'ἳ'=>['ι',0b1010000],
+  'Ἳ'=>['ι',0b1010001],
   'ἷ'=>['ι',0b1011000],
+  'Ἷ'=>['ι',0b1011001],
   'κ'=>['κ',0b0],
   'Κ'=>['κ',0b1],
   'λ'=>['λ',0b0],
@@ -1250,11 +1195,15 @@ JSON
   'ο'=>['ο',0b0],
   'Ο'=>['ο',0b1],
   'ό'=>['ο',0b1000],
+  'Ό'=>['ο',0b1001],
   'ὸ'=>['ο',0b10000],
+  'Ὸ'=>['ο',0b10001],
   'ὀ'=>['ο',0b100000],
   'Ὀ'=>['ο',0b100001],
   'ὄ'=>['ο',0b101000],
   'Ὄ'=>['ο',0b101001],
+  'ὂ'=>['ο',0b110000],
+  'Ὂ'=>['ο',0b110001],
   'ὁ'=>['ο',0b1000000],
   'Ὁ'=>['ο',0b1000001],
   'ὅ'=>['ο',0b1001000],
@@ -1276,9 +1225,12 @@ JSON
   'υ'=>['υ',0b0],
   'Υ'=>['υ',0b1],
   'ϋ'=>['υ',0b10],
+  'Ϋ'=>['υ',0b11],
   'ύ'=>['υ',0b1000],
+  'Ύ'=>['υ',0b1001],
   'ΰ'=>['υ',0b1010],
   'ὺ'=>['υ',0b10000],
+  'Ὺ'=>['υ',0b10001],
   'ῢ'=>['υ',0b10010],
   'ῦ'=>['υ',0b11000],
   'ὐ'=>['υ',0b100000],
@@ -1289,7 +1241,9 @@ JSON
   'ὕ'=>['υ',0b1001000],
   'Ὕ'=>['υ',0b1001001],
   'ὓ'=>['υ',0b1010000],
+  'Ὓ'=>['υ',0b1010001],
   'ὗ'=>['υ',0b1011000],
+  'Ὗ'=>['υ',0b1011001],
   'φ'=>['φ',0b0],
   'Φ'=>['φ',0b1],
   'χ'=>['χ',0b0],
@@ -1300,8 +1254,10 @@ JSON
   'Ω'=>['ω',0b1],
   'ῳ'=>['ω',0b100],
   'ώ'=>['ω',0b1000],
+  'Ώ'=>['ω',0b1001],
   'ῴ'=>['ω',0b1100],
   'ὼ'=>['ω',0b10000],
+  'Ὼ'=>['ω',0b10001],
   'ῶ'=>['ω',0b11000],
   'ῷ'=>['ω',0b11100],
   'ὠ'=>['ω',0b100000],
@@ -1311,15 +1267,19 @@ JSON
   'Ὤ'=>['ω',0b101001],
   'ᾤ'=>['ω',0b101100],
   'ὢ'=>['ω',0b110000],
+  'Ὢ'=>['ω',0b110001],
   'ὦ'=>['ω',0b111000],
   'Ὦ'=>['ω',0b111001],
   'ᾦ'=>['ω',0b111100],
   'ὡ'=>['ω',0b1000000],
   'Ὡ'=>['ω',0b1000001],
+  'ᾡ'=>['ω',0b1000100],
   'ὥ'=>['ω',0b1001000],
   'Ὥ'=>['ω',0b1001001],
+  'ᾥ'=>['ω',0b1001100],
   'ὣ'=>['ω',0b1010000],
   'Ὣ'=>['ω',0b1010001],
+  'ᾣ'=>['ω',0b1010100],
   'ὧ'=>['ω',0b1011000],
   'Ὧ'=>['ω',0b1011001],
   'ᾧ'=>['ω',0b1011100],
@@ -1327,16 +1287,21 @@ JSON
   'Ϝ'=>['ϝ',0b1]
 }
 @@assemble_greek_char_hash = {
-
   'α00'=>'α',
   'α01'=>'Α',
   'α04'=>'ᾳ',
   'α08'=>'ά',
+  'α09'=>'Ά',
+  'α0c'=>'ᾴ',
   'α10'=>'ὰ',
+  'α11'=>'Ὰ',
+  'α14'=>'ᾲ',
   'α18'=>'ᾶ',
   'α1c'=>'ᾷ',
   'α20'=>'ἀ',
   'α21'=>'Ἀ',
+  'α24'=>'ᾀ',
+  'α25'=>'ᾈ',
   'α28'=>'ἄ',
   'α29'=>'Ἄ',
   'α2c'=>'ᾄ',
@@ -1346,10 +1311,14 @@ JSON
   'α39'=>'Ἆ',
   'α40'=>'ἁ',
   'α41'=>'Ἁ',
+  'α44'=>'ᾁ',
+  'α45'=>'ᾉ',
   'α48'=>'ἅ',
   'α49'=>'Ἅ',
   'α4c'=>'ᾅ',
+  'α4d'=>'ᾍ',
   'α50'=>'ἃ',
+  'α51'=>'Ἃ',
   'α5c'=>'ᾇ',
   'β00'=>'β',
   'β01'=>'Β',
@@ -1360,25 +1329,31 @@ JSON
   'ε00'=>'ε',
   'ε01'=>'Ε',
   'ε08'=>'έ',
+  'ε09'=>'Έ',
   'ε10'=>'ὲ',
+  'ε11'=>'Ὲ',
   'ε20'=>'ἐ',
   'ε21'=>'Ἐ',
   'ε28'=>'ἔ',
   'ε29'=>'Ἔ',
   'ε30'=>'ἒ',
+  'ε31'=>'Ἒ',
   'ε40'=>'ἑ',
   'ε41'=>'Ἑ',
   'ε48'=>'ἕ',
   'ε49'=>'Ἕ',
   'ε50'=>'ἓ',
+  'ε51'=>'Ἓ',
   'ζ00'=>'ζ',
   'ζ01'=>'Ζ',
   'η00'=>'η',
   'η01'=>'Η',
   'η04'=>'ῃ',
   'η08'=>'ή',
+  'η09'=>'Ή',
   'η0c'=>'ῄ',
   'η10'=>'ὴ',
+  'η11'=>'Ὴ',
   'η14'=>'ῂ',
   'η18'=>'ῆ',
   'η1c'=>'ῇ',
@@ -1389,6 +1364,7 @@ JSON
   'η29'=>'Ἤ',
   'η2c'=>'ᾔ',
   'η30'=>'ἢ',
+  'η31'=>'Ἢ',
   'η38'=>'ἦ',
   'η39'=>'Ἦ',
   'η3c'=>'ᾖ',
@@ -1400,6 +1376,7 @@ JSON
   'η4c'=>'ᾕ',
   'η50'=>'ἣ',
   'η51'=>'Ἣ',
+  'η54'=>'ᾓ',
   'η58'=>'ἧ',
   'η59'=>'Ἧ',
   'η5c'=>'ᾗ',
@@ -1408,9 +1385,12 @@ JSON
   'ι00'=>'ι',
   'ι01'=>'Ι',
   'ι02'=>'ϊ',
+  'ι03'=>'Ϊ',
   'ι08'=>'ί',
+  'ι09'=>'Ί',
   'ι0a'=>'ΐ',
   'ι10'=>'ὶ',
+  'ι11'=>'Ὶ',
   'ι12'=>'ῒ',
   'ι18'=>'ῖ',
   'ι1a'=>'ῗ',
@@ -1419,6 +1399,7 @@ JSON
   'ι28'=>'ἴ',
   'ι29'=>'Ἴ',
   'ι30'=>'ἲ',
+  'ι31'=>'Ἲ',
   'ι38'=>'ἶ',
   'ι39'=>'Ἶ',
   'ι40'=>'ἱ',
@@ -1426,7 +1407,9 @@ JSON
   'ι48'=>'ἵ',
   'ι49'=>'Ἵ',
   'ι50'=>'ἳ',
+  'ι51'=>'Ἳ',
   'ι58'=>'ἷ',
+  'ι59'=>'Ἷ',
   'κ00'=>'κ',
   'κ01'=>'Κ',
   'λ00'=>'λ',
@@ -1440,11 +1423,15 @@ JSON
   'ο00'=>'ο',
   'ο01'=>'Ο',
   'ο08'=>'ό',
+  'ο09'=>'Ό',
   'ο10'=>'ὸ',
+  'ο11'=>'Ὸ',
   'ο20'=>'ὀ',
   'ο21'=>'Ὀ',
   'ο28'=>'ὄ',
   'ο29'=>'Ὄ',
+  'ο30'=>'ὂ',
+  'ο31'=>'Ὂ',
   'ο40'=>'ὁ',
   'ο41'=>'Ὁ',
   'ο48'=>'ὅ',
@@ -1466,9 +1453,12 @@ JSON
   'υ00'=>'υ',
   'υ01'=>'Υ',
   'υ02'=>'ϋ',
+  'υ03'=>'Ϋ',
   'υ08'=>'ύ',
+  'υ09'=>'Ύ',
   'υ0a'=>'ΰ',
   'υ10'=>'ὺ',
+  'υ11'=>'Ὺ',
   'υ12'=>'ῢ',
   'υ18'=>'ῦ',
   'υ20'=>'ὐ',
@@ -1479,7 +1469,9 @@ JSON
   'υ48'=>'ὕ',
   'υ49'=>'Ὕ',
   'υ50'=>'ὓ',
+  'υ51'=>'Ὓ',
   'υ58'=>'ὗ',
+  'υ59'=>'Ὗ',
   'φ00'=>'φ',
   'φ01'=>'Φ',
   'χ00'=>'χ',
@@ -1490,8 +1482,10 @@ JSON
   'ω01'=>'Ω',
   'ω04'=>'ῳ',
   'ω08'=>'ώ',
+  'ω09'=>'Ώ',
   'ω0c'=>'ῴ',
   'ω10'=>'ὼ',
+  'ω11'=>'Ὼ',
   'ω18'=>'ῶ',
   'ω1c'=>'ῷ',
   'ω20'=>'ὠ',
@@ -1501,15 +1495,19 @@ JSON
   'ω29'=>'Ὤ',
   'ω2c'=>'ᾤ',
   'ω30'=>'ὢ',
+  'ω31'=>'Ὢ',
   'ω38'=>'ὦ',
   'ω39'=>'Ὦ',
   'ω3c'=>'ᾦ',
   'ω40'=>'ὡ',
   'ω41'=>'Ὡ',
+  'ω44'=>'ᾡ',
   'ω48'=>'ὥ',
   'ω49'=>'Ὥ',
+  'ω4c'=>'ᾥ',
   'ω50'=>'ὣ',
   'ω51'=>'Ὣ',
+  'ω54'=>'ᾣ',
   'ω58'=>'ὧ',
   'ω59'=>'Ὧ',
   'ω5c'=>'ᾧ',

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: tinycus
 version: !ruby/object:Gem::Version
-  version: 1.0.9
+  version: 1.1.0
 platform: ruby
 authors:
 - Benjamin Crowell
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-01-15 00:00:00.000000000 Z
+date: 2024-01-25 00:00:00.000000000 Z
 dependencies: []
 description: "This is a ruby library to do some string functions efficiently that\nwould
   otherwise be slow or require a huge footprint. For example,\nit can remove accents
@@ -16,9 +16,7 @@ description: "This is a ruby library to do some string functions efficiently tha
 email: 
 executables: []
 extensions: []
-extra_rdoc_files:
-- README.md
-- tinycus.rb
+extra_rdoc_files: []
 files:
 - LICENSE
 - README.md
@@ -30,11 +28,7 @@ metadata:
   contact_uri: http://lightandmatter.com/area4author.html
   documentation_uri: https://bitbucket.org/ben-crowell/tinycus
 post_install_message: 
-rdoc_options:
-- "--exclude"
-- "(bad_combining|generating)"
-- "--main"
-- README.md
+rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement