glaemscribe 1.0.13 → 1.0.14

data/lib/api/post_processor/csub.rb

@@ -0,0 +1,64 @@
+# encoding: UTF-8
+#
+# Glǽmscribe (also written Glaemscribe) is a software dedicated to
+# the transcription of texts between writing systems, and more 
+# specifically dedicated to the transcription of J.R.R. Tolkien's 
+# invented languages to some of his devised writing systems.
+# 
+# Copyright (C) 2015 Benjamin Babut (Talagan).
+# 
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+# 
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+module Glaemscribe
+  module API
+
+    class CSubPostProcessorOperator < PostProcessorOperator
+      attr_reader :matcher
+      attr_reader :triggers
+      
+      def initialize(args)
+        super(args)
+        
+        # Build our operator
+        @matcher     = self.raw_args[0]
+        @triggers    = Hash.new
+  
+        self.raw_args.each{ |arg|
+
+          splitted  = arg.split()   
+          replacer  = splitted.shift()
+    
+          splitted.each{ |token|
+            @triggers[token] = replacer
+          }
+        }
+      end
+    
+      def apply(tokens)
+        last_trigger_replacer = nil
+        tokens.each_with_index{ |token,idx|
+          if token == @matcher && last_trigger_replacer != nil
+            tokens[idx] = last_trigger_replacer
+          elsif @triggers[token] != nil
+            last_trigger_replacer = @triggers[token]
+          end
+        }
+        tokens
+      end
+    end
+
+    ResourceManager::register_post_processor_class("csub", CSubPostProcessorOperator)    
+
+  end
+end

data/lib/api/post_processor/reverse.rb

@@ -24,9 +24,8 @@ module Glaemscribe
   module API
 
     class ReversePostProcessorOperator < PostProcessorOperator
-      
-      def apply(l)
-        l.reverse
+      def apply(tokens)
+        tokens.reverse
       end
     end
 

data/lib/api/sheaf.rb

@@ -35,6 +35,8 @@ module Glaemscribe
       attr_reader :sheaf_chain 
       attr_reader :mode
       attr_reader :rule
+      
+      attr_reader :expression
        
       SHEAF_SEPARATOR    = "*"
       

data/lib/api/sheaf_chain.rb

@@ -49,6 +49,8 @@ module Glaemscribe
       attr_reader :mode
       attr_reader :rule
       
+      attr_reader :expression
+      
       def src? ; is_src ; end
       def dst? ; !is_src ; end
                  

data/lib/api/transcription_pre_post_processor.rb

@@ -25,6 +25,7 @@ module Glaemscribe
     
     class PrePostProcessorOperator
       attr_reader :args
+      attr_reader :raw_args
       
       def initialize(raw_args)
         @raw_args = raw_args
@@ -46,7 +47,7 @@ module Glaemscribe
         }
       end
       
-      def apply(l)
+      def apply
         raise "Pure virtual method, should be overloaded."
       end
     end
@@ -90,7 +91,16 @@ module Glaemscribe
           op.finalize(trans_options)
         }
       end
-      
+
+    end
+    
+    class PreProcessorOperator < PrePostProcessorOperator  
+    end
+   
+    class PostProcessorOperator < PrePostProcessorOperator
+    end
+    
+    class TranscriptionPreProcessor < TranscriptionPrePostProcessor           
       # Apply all preprocessor rules consecutively
       def apply(l)
         ret = l
@@ -99,19 +109,39 @@ module Glaemscribe
         } 
         ret
       end
-      
-    end
-    
-    class PreProcessorOperator < PrePostProcessorOperator
-    end
-    
-    class TranscriptionPreProcessor < TranscriptionPrePostProcessor      
-    end
-    
-    class PostProcessorOperator < PrePostProcessorOperator
     end
     
-    class TranscriptionPostProcessor < TranscriptionPrePostProcessor      
+    class TranscriptionPostProcessor < TranscriptionPrePostProcessor
+      
+      attr_accessor :out_space
+          
+      def apply(tokens, out_charset)
+        
+        out_space_str     = " "
+        out_space_str     = @out_space.map{ |token| out_charset[token].str }.join("") if @out_space
+         
+        # Apply filters
+        @operators.each{ |operator|
+          tokens = operator.apply(tokens)
+        } 
+        
+        # Convert output
+        ret = ""
+        tokens.each{ |token|
+          case token 
+            when ""
+            when "*UNKNOWN"
+               ret += UNKNOWN_CHAR_OUTPUT
+            when "*SPACE"
+                ret += out_space_str
+            when "*LF"
+               ret += "\n"
+            else
+               ret += out_charset[token].str
+          end        
+        }
+        ret
+      end  
     end   
     
   end

data/lib/api/transcription_processor.rb

@@ -26,9 +26,7 @@ module Glaemscribe
            
       attr_reader   :rule_groups
       attr_reader   :mode
-      
-      attr_accessor :out_space
-      
+            
       def initialize(mode)
         @mode         = mode
         @rule_groups  = {}
@@ -58,7 +56,7 @@ module Glaemscribe
           rg.in_charset.each{ |char, group|
             group_for_char = @in_charset[char]
             if group_for_char
-              mode.errors << "Group #{rgname} uses input character #{char} which is also used by group #{group_for_char.name}. Input charsets should not intersect between groups." 
+              mode.errors << Glaeml::Error.new(-1,"Group #{rgname} uses input character #{char} which is also used by group #{group_for_char.name}. Input charsets should not intersect between groups.") 
             else
               @in_charset[char] = group
             end
@@ -75,24 +73,23 @@ module Glaemscribe
         }        
       end
       
-      def apply(l, out_charset)
-        ret = ""
+      def apply(l)
+        ret = []
         current_group     = nil
         accumulated_word  = ""
-        
-        out_space_str     = " "
-        out_space_str     = @out_space.map{ |token| out_charset[token].str }.join("") if @out_space
-        
+       
         l.split("").each{ |c|
           case c
           when " ", "\t" 
-            ret += transcribe_word(accumulated_word, out_charset)
-            ret += out_space_str
+            ret += transcribe_word(accumulated_word)
+            ret += ["*SPACE"]
             
             accumulated_word = ""
-          when "\r", "\n"
-            ret += transcribe_word(accumulated_word, out_charset)
-            ret += c
+          when "\r"
+            # Ignore
+          when "\n"
+            ret += transcribe_word(accumulated_word)
+            ret += ["*LF"]
             
             accumulated_word = ""
           else
@@ -100,18 +97,18 @@ module Glaemscribe
             if c_group == current_group
               accumulated_word += c
             else
-              ret += transcribe_word(accumulated_word, out_charset)
+              ret += transcribe_word(accumulated_word)
               current_group    = c_group
               accumulated_word = c
             end
           end            
         }
         # Just in case
-        ret += transcribe_word(accumulated_word, out_charset)
+        ret += transcribe_word(accumulated_word)
         ret
       end
       
-      def transcribe_word(word, out_charset)
+      def transcribe_word(word)
         res = []
         word = WORD_BOUNDARY + word + WORD_BOUNDARY
         while word.length != 0
@@ -119,17 +116,8 @@ module Glaemscribe
           word = word[len..-1]
           res += r
         end
-        ret = ""
-        res.each{ |token|
-          case token 
-          when ""
-          when UNKNOWN_CHAR_OUTPUT
-            ret += UNKNOWN_CHAR_OUTPUT
-          else
-            ret += out_charset[token].str
-          end        
-        }
-        ret
+        # Return token list
+        res
       end
       
     end

data/lib/api/transcription_tree_node.rb

@@ -84,7 +84,7 @@ module Glaemscribe
         end
       
         # Only the root node is in the chain, we could not find anything; return the "unknown char"
-        return [UNKNOWN_CHAR_OUTPUT], 1    
+        return ["*UNKNOWN"], 1    
       end
     end
   end

data/lib/glaemscribe.rb

@@ -65,6 +65,7 @@ module Glaemscribe
     require API_PATH + "/api/pre_processor/rxsubstitute.rb"
     require API_PATH + "/api/pre_processor/up_down_tehta_split.rb"
     require API_PATH + "/api/post_processor/reverse.rb"
+    require API_PATH + "/api/post_processor/csub.rb"
     
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: glaemscribe
 version: !ruby/object:Gem::Version
-  version: 1.0.13
+  version: 1.0.14
 platform: ruby
 authors:
 - Benjamin 'Talagan' Babut
@@ -44,6 +44,9 @@ files:
 - glaemresources/modes/adunaic.glaem
 - glaemresources/modes/blackspeech-annatar.glaem
 - glaemresources/modes/blackspeech.glaem
+- glaemresources/modes/futhark-long-branch.glaem.disabled
+- glaemresources/modes/futhark-short-twig.glaem.disabled
+- glaemresources/modes/futhorc.glaem.disabled
 - glaemresources/modes/gothic.glaem
 - glaemresources/modes/khuzdul.glaem
 - glaemresources/modes/mercian.glaem
@@ -69,6 +72,7 @@ files:
 - lib/api/mode.rb
 - lib/api/mode_parser.rb
 - lib/api/option.rb
+- lib/api/post_processor/csub.rb
 - lib/api/post_processor/reverse.rb
 - lib/api/pre_processor/downcase.rb
 - lib/api/pre_processor/elvish_numbers.rb