glaemscribe 1.0.15 → 1.0.16

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 6b544df6b9e371a154053782d11e9f390c9e1dda
-  data.tar.gz: 63efe49edc9c42c7e8b5b0f75b65ac36b5591b7c
+  metadata.gz: 5aa0d9e7fab6fa5fe2c50f84c90fdcfb94bd423b
+  data.tar.gz: 5fffb9618dd05644bee52429073a44d0d40af0d5
 SHA512:
-  metadata.gz: bb17be62e81701fd9b649df2f894e789c78eeaf38c185fe9fbd0bf936a0db53ba386f767c708ef8318b7265e6202bc5c4c77f9ed3750cf47a44ae0ac75a2ce86
-  data.tar.gz: 256a18b0199dccfe1d5f66190cc7b6f7dff108c546b644828473496fb8f697244804021173900b112ac2a2dc20a97e19c9b8f286c8af4bd8e814c933e1677a47
+  metadata.gz: 764a4736e61caa7a8cf485741f65a24be731d9db2a834160cf25321741a9f27cbb7c3f7d1b9c9bf7f5945891fe4827527a38709ae2f85ac422f2030f67612c80
+  data.tar.gz: 0b83ebe3596cb8313c2c7b5e2f2df5c9ce7b7c5912f0c4a32d3c6fd4156eaa3e977623a31c494581d0342fe2aae342cdf36644d5dbfffc588277315ce91638b5

data/bin/glaemscribe

@@ -107,7 +107,7 @@ command :transcribe do |c|
   
   c.syntax      = 'glaemscribe transcribe file [options]'
   c.summary     = 'Transcribes a file (default command)'
-  c.description = "Transcribes a file with the given options. You can use '-' instead of a file name to work with stdin."
+  c.description = "Transcribes a file with the given options. You can use 'STDIN' instead of a file name to work with stdin."
    
   c.option '-m',  '--mode mode',                 String, "The name of the embedded mode to use. See the 'list' command to get a list of available modes names."
   c.option '-c',  '--charset charset',           String, 'The name of the charset to use. If not given, glaemscribe will load and use the default charset defined in the mode.' 
@@ -224,7 +224,7 @@ command :transcribe do |c|
     
     # Ready for transcription ...
   
-    if(filename == "-")
+    if(filename == "STDIN")
       perxit "Opened in stdin mode, waiting for input..."
       begin
         while to_transcribe = STDIN.gets
@@ -302,7 +302,14 @@ command :info do |c|
     puts "#{$terminal.color "Human Name" , :bold} : #{mode.human_name}"
     puts "#{$terminal.color "Authors   " , :bold} : #{mode.authors}"
     puts "#{$terminal.color "Version   " , :bold} : #{mode.version}"
-      
+    puts ""
+    puts "#{$terminal.color "Options   " , :bold} :"
+    mode.options.each { |name,option|
+      puts "  #{$terminal.color name, :bold} (#{option.type}) [#{option.default_value_name}]"
+      option.values.each{ |oname,ovalue|
+        puts "    #{$terminal.color oname, :bold}"
+      }
+    }
   end
   
 end

data/glaemresources/charsets/tengwar_ds.cst

@@ -31,7 +31,9 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   mainly, tehtar variants. These characters are only virtual, they do not really exist in DS based fonts.
 **\
 
-\** ☢ **\ \char 2622 A_TEHTA A_TEHTA_CIRCUM E_TEHTA I_TEHTA O_TEHTA U_TEHTA THSUP_TICK_INV THSUP_LAMBDA THSUP_TICK THINF_CURL THSUP_SEV THINF_DOT THINF_DDOT THINF_TDOT THINF_STROKE THINF_DSTROKE
+\** ☢  
+  \char 2622 A_TEHTA A_TEHTA_CIRCUM E_TEHTA I_TEHTA O_TEHTA U_TEHTA THSUP_TICK_INV THSUP_LAMBDA THSUP_TICK THINF_CURL THSUP_SEV THINF_DOT THINF_DDOT THINF_TDOT THINF_STROKE THINF_DSTROKE DASH_INF SHOOK_LEFT SHOOK_RIGHT
+**\
 
 \**   **\ \char 20 SPACE              
 \** ! **\ \char 21 TW_EXT_11            
@@ -324,4 +326,85 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \** 倦 **\ \char 5026 ?                                
 \** 倰 **\ \char 5030 ?                                
 \** 倹 **\ \char 5039 ?
+
+
+\** The following virtual chars are used to handle tehtar (& the like) multiple version chosing **\
+\** It could be avoided with modern fonts with gsub/gpos tables for ligatures and diacritics **\
+\** placement **\
+
+\** TODO : Move FORMEN to S, move HYARMEN to XS **\
+
+\beg virtual A_TEHTA
+  \class A_TEHTA_XS   TELCO ARA
+  \class A_TEHTA_S    ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN
+  \class A_TEHTA_L    TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN
+  \class A_TEHTA_XL   TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME
+\end
+
+\beg virtual A_TEHTA_CIRCUM
+  \class A_TEHTA_CIRCUM_XS   TELCO ARA
+  \class A_TEHTA_CIRCUM_S    ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN
+  \class A_TEHTA_CIRCUM_L    TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN
+  \class A_TEHTA_CIRCUM_XL   TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME
+\end
+
+\beg virtual E_TEHTA
+  \class E_TEHTA_XS   TELCO ARA
+  \class E_TEHTA_S    ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN
+  \class E_TEHTA_L    TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN
+  \class E_TEHTA_XL   TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME
+\end
+
+\beg virtual I_TEHTA
+  \class I_TEHTA_XS   TELCO ARA
+  \class I_TEHTA_S    ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN
+  \class I_TEHTA_L    TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN
+  \class I_TEHTA_XL   TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME
+\end
+
+\beg virtual O_TEHTA
+  \class O_TEHTA_XS   TELCO ARA
+  \class O_TEHTA_S    ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN
+  \class O_TEHTA_L    TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN
+  \class O_TEHTA_XL   TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME
+\end
+
+\beg virtual U_TEHTA
+  \class U_TEHTA_XS   TELCO ARA
+  \class U_TEHTA_S    ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN
+  \class U_TEHTA_L    TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN
+  \class U_TEHTA_XL   TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME
+\end
+
+\** no vowel mark **\
+\beg virtual NO_VOWEL_DOT
+  \class THINF_DOT_XS     TELCO ROMEN ARDA
+  \class THINF_DOT_L      ORE TW_EXT_11 TW_EXT_12  TINCO PARMA SULE FORMEN VALA ANNA VILYA SILME ESSE AHA HWESTA HYARMEN YANTA URE
+  \class THINF_DOT_XL     QUESSE CALMA TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME 
+  \class LAMBE_MARK_DOT   LAMBE ALDA
+\end
+
+\** palatalisation **\
+\beg virtual PALATAL_SIGN
+  \class THINF_DDOT_XS    ROMEN
+  \class THINF_DDOT_S 
+  \class THINF_DDOT_L     TINCO PARMA HYARMEN ANNA
+  \class THINF_DDOT_XL    ANDO ANTO NUMEN MALTA
+  \class LAMBE_MARK_DDOT  LAMBE
+\end
+
+\** gemination **\
+\beg virtual GEMINATE_SIGN
+  \class DASH_INF_XS
+  \class DASH_INF_S       TINCO PARMA CALMA ROMEN HWESTA SULE
+  \class DASH_INF_L       NUMEN MALTA UNGWE ANDO 
+  \class DASH_INF_XL
+  \class LAMBE_MARK_TILD  LAMBE
+\end
+
+\beg virtual ALVEOLAR_SIGN
+  \class SHOOK_LEFT_L   CALMA
+  \class SHOOK_RIGHT_L  TINCO PARMA   
+\end
+
              

data/glaemresources/modes/adunaic.glaem

@@ -22,14 +22,16 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 **\
 
-\** Changelog **\
-\** 0.0.2 : added option for o/u tehtar loop orientation **\
+\beg changelog
+ \entry "0.0.2", "Added option for o/u tehtar loop orientation"
+ \entry "0.0.3", "Normalizing to virtual chars" 
+\end
 
 \**  Adunaic mode for glaemscribe (MAY BE INCOMPLETE) **\
 \language Adûnaic
 \writing  Tengwar
 \mode     Glaemscrafu
-\version  0.0.2
+\version  0.0.3
 \authors  "Talagan (Benjamin Babut)"
 
 \charset  tengwar_ds true
@@ -97,50 +99,32 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     {OOU} === {OO}{U} \** ôu **\
         
     \if "reverse_o_u_tehtar == U_UP_O_DOWN"
-        {O_LOOP_XS} === O_TEHTA_XS
-        {O_LOOP_S}  === O_TEHTA_S
-        {O_LOOP_L}  === O_TEHTA_L
-        {O_LOOP_XL} === O_TEHTA_XL
-        {U_LOOP_XS} === U_TEHTA_XS
-        {U_LOOP_S}  === U_TEHTA_S
-        {U_LOOP_L}  === U_TEHTA_L
-        {U_LOOP_XL} === U_TEHTA_XL  
+      {O_LOOP} === O_TEHTA
+      {U_LOOP} === U_TEHTA
     \else
-        {O_LOOP_XS} === U_TEHTA_XS
-        {O_LOOP_S}  === U_TEHTA_S
-        {O_LOOP_L}  === U_TEHTA_L
-        {O_LOOP_XL} === U_TEHTA_XL
-        {U_LOOP_XS} === O_TEHTA_XS
-        {U_LOOP_S}  === O_TEHTA_S
-        {U_LOOP_L}  === O_TEHTA_L
-        {U_LOOP_XL} === O_TEHTA_XL    
+      {O_LOOP} === U_TEHTA
+      {U_LOOP} === O_TEHTA
     \endif
         
-    {SDIPHTHONGS}  === {AI}            * {AU}
-    {SDIPHTHENGS}  === YANTA A_TEHTA_L  * URE A_TEHTA_L 
+    {SDIPHTHONGS}  === {AI}           * {AU}
+    {SDIPHTHENGS}  === YANTA A_TEHTA  * URE A_TEHTA 
                    
-    {LDIPHTHONGS}  === {AAI}                  * {AAU}                 * {EEI}                 * {EEU}               * {OOI}                 * {OOU}
-    {LDIPHTHENGS}  === ARA A_TEHTA_XS YANTA   * ARA A_TEHTA_XS URE    * ARA E_TEHTA_XS YANTA  * ARA E_TEHTA_XS URE  * ARA {O_LOOP_XS} YANTA  * ARA {O_LOOP_XS} URE
+    {LDIPHTHONGS}  === {AAI}               * {AAU}              * {EEI}              * {EEU}            * {OOI}               * {OOU}
+    {LDIPHTHENGS}  === ARA A_TEHTA YANTA   * ARA A_TEHTA URE    * ARA E_TEHTA YANTA  * ARA E_TEHTA URE  * ARA {O_LOOP} YANTA  * ARA {O_LOOP} URE
                                                                                                                  
-    {VOWELS}      === {A}         * {E}         * {I}           * {O}           * {U}    
-    {TEHTA_XS}    === A_TEHTA_XS  * E_TEHTA_XS  * I_TEHTA_XS    * {O_LOOP_XS}   * {U_LOOP_XS} 
-    {TEHTA__S}    === A_TEHTA_S   * E_TEHTA_S   * I_TEHTA_S     * {O_LOOP_S}    * {U_LOOP_S} 
-    {TEHTA__L}    === A_TEHTA_L   * E_TEHTA_L   * I_TEHTA_L     * {O_LOOP_L}    * {U_LOOP_L} 
-    {TEHTA_XL}    === A_TEHTA_XL  * E_TEHTA_XL  * I_TEHTA_XL    * {O_LOOP_XL}   * {U_LOOP_XL} 
+    {VOWELS}      === {A}          * {E}          * {I}          * {O}          * {U}    
+    {_TEHTAR_}    === A_TEHTA      * E_TEHTA      *  I_TEHTA     * {O_LOOP}     * {U_LOOP}
                    
-    {LVOWELS}     === {AA}            * {EE}            * {II}            * {OO}            * {UU}
-    {LVOWTNG}     === ARA A_TEHTA_XS  * ARA E_TEHTA_XS  * ARA I_TEHTA_XS  * ARA {O_LOOP_XS} * ARA {U_LOOP_XS} 
+    {LVOWELS}     === {AA}         * {EE}         * {II}         * {OO}         * {UU}
+    {LVOWTNG}     === ARA A_TEHTA  * ARA E_TEHTA  * ARA I_TEHTA  * ARA {O_LOOP} * ARA {U_LOOP} 
 
     \** Let' put all vowels/diphthongs in the same basket **\
     {V_D}         === [ {VOWELS}    * {LVOWELS} * {SDIPHTHONGS} * {LDIPHTHONGS} ]        
     \** And their images... **\            
-    {T_XS_D}      === [ {TEHTA_XS}  * {LVOWTNG} * {SDIPHTHENGS} * {LDIPHTHENGS} ]
-    {T_S_D}       === [ {TEHTA__S}  * {LVOWTNG} * {SDIPHTHENGS} * {LDIPHTHENGS} ]
-    {T_L_D}       === [ {TEHTA__L}  * {LVOWTNG} * {SDIPHTHENGS} * {LDIPHTHENGS} ]
-    {T_XL_D}      === [ {TEHTA_XL}  * {LVOWTNG} * {SDIPHTHENGS} * {LDIPHTHENGS} ]
-
-    [{VOWELS}]      --> TELCO [{TEHTA_XS}]   \** Replace isolated short vowels **\
-    [{LVOWELS}]     --> [{LVOWTNG}]    \** Replace long vowels **\
+    {_V_D_}       === [ {_TEHTAR_}  * {LVOWTNG} * {SDIPHTHENGS} * {LDIPHTHENGS} ]
+  
+    [{VOWELS}]       --> TELCO [{_TEHTAR_}]   \** Replace isolated short vowels **\
+    [{LVOWELS}]      --> [{LVOWTNG}]    \** Replace long vowels **\
     [{SDIPHTHONGS}]  --> [{SDIPHTHENGS}]  \** Replace short diphthongs **\
     [{LDIPHTHONGS}]  --> [{LDIPHTHENGS}]  \** Replace long diphthongs **\
 
@@ -150,64 +134,64 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     {K}   === (c,k)
     {V}   === (v,w)
 
-    {L1_S}         === {K}     * p     * t     * {K}{K}            * pp                * tt
-    {L1_T}         === QUESSE  * PARMA * TINCO * CALMA DASH_INF_S  * PARMA DASH_INF_S  * TINCO  DASH_INF_S
+    {L1_S}         === {K}     * p     * t     * {K}{K}               * pp                   * tt
+    {L1_T}         === QUESSE  * PARMA * TINCO * CALMA GEMINATE_SIGN  * PARMA GEMINATE_SIGN  * TINCO  GEMINATE_SIGN
     
     [{L1_S}]       -->  [ {L1_T} ]
-    [{L1_S}]{V_D}  -->  [ {L1_T} ]{T_S_D} 
+    [{L1_S}]{V_D}  -->  [ {L1_T} ]{_V_D_} 
 
-    {L2_S}         === d    * b     * g     * dd              * bb                * gg
-    {L2_T}         === ANDO * UMBAR * UNGWE * ANDO DASH_INF_L * UMBAR DASH_INF_L  * UNGWE DASH_INF_L
+    {L2_S}         === d    * b     * g     * dd                 * bb                   * gg
+    {L2_T}         === ANDO * UMBAR * UNGWE * ANDO GEMINATE_SIGN * UMBAR GEMINATE_SIGN  * UNGWE GEMINATE_SIGN
     [{L2_S}]       --> [{L2_T}] 
-    [{L2_S}]{V_D}  --> [{L2_T}]{T_XL_D} 
+    [{L2_S}]{V_D}  --> [{L2_T}]{_V_D_} 
 
     \** Alignment of tehta is not the same in the font **\
     \** So we need to split the third line unfortunately **\
-    {L3_1_S}          === th    * ph      * (t,th)th          * (p,ph)ph            * (t,th)ph    * (k,kh)ph      * (p,ph)th    * (k,kh)th
-    {L3_1_T}          === SULE  * FORMEN  * SULE DASH_INF_S   * FORMEN DASH_INF_S   * SULE FORMEN * HWESTA FORMEN * FORMEN SULE * HWESTA SULE
+    {L3_1_S}          === th    * ph      * (t,th)th             * (p,ph)ph               * (t,th)ph    * (k,kh)ph      * (p,ph)th    * (k,kh)th
+    {L3_1_T}          === SULE  * FORMEN  * SULE GEMINATE_SIGN   * FORMEN GEMINATE_SIGN   * SULE FORMEN * HWESTA FORMEN * FORMEN SULE * HWESTA SULE
    
-    {L3_2_S}          === sh    * kh      * (k,kh)kh          * (p,ph)kh            * (t,th)kh
-    {L3_2_T}          === AHA   * HWESTA  * HWESTA DASH_INF_S * FORMEN HWESTA       * SULE HWESTA
+    {L3_2_S}          === sh    * kh      * (k,kh)kh             * (p,ph)kh            * (t,th)kh
+    {L3_2_T}          === AHA   * HWESTA  * HWESTA GEMINATE_SIGN * FORMEN HWESTA       * SULE HWESTA
    
     [{L3_1_S}]        --> [{L3_1_T}] 
-    [{L3_1_S}]{V_D}   --> [{L3_1_T}]{T_S_D} 
+    [{L3_1_S}]{V_D}   --> [{L3_1_T}]{_V_D_} 
     [{L3_2_S}]        --> [{L3_2_T}] 
-    [{L3_2_S}]{V_D}   --> [{L3_2_T}]{T_L_D} 
+    [{L3_2_S}]{V_D}   --> [{L3_2_T}]{_V_D_} 
 
     {L4_S}            === nd    * mb    * ng
     {L4_T}            === ANTO  * AMPA  * UNQUE
     [{L4_S}]          --> [{L4_T}] 
-    [{L4_S}]{V_D}     --> [{L4_T}]{T_XL_D} 
+    [{L4_S}]{V_D}     --> [{L4_T}]{_V_D_} 
 
-    {L5_S}            === n     * m     * nn                * mm
-    {L5_T}            === NUMEN * MALTA * NUMEN DASH_INF_L  * MALTA DASH_INF_L
+    {L5_S}            === n     * m     * nn                    * mm
+    {L5_T}            === NUMEN * MALTA * NUMEN GEMINATE_SIGN   * MALTA GEMINATE_SIGN
     [{L5_S}]          --> [{L5_T}] 
-    [{L5_S}]{V_D}     --> [{L5_T}]{T_XL_D} 
+    [{L5_S}]{V_D}     --> [{L5_T}]{_V_D_} 
 
-    {L6_S}            === {V}   * y     * rr                * {V}{V}            * yy
-    {L6_T}            === VALA  * ANNA  * ROMEN DASH_INF_S  * VALA DASH_INF_S   * ANNA DASH_INF_S
+    {L6_S}            === {V}   * y     * rr                    * {V}{V}                * yy
+    {L6_T}            === VALA  * ANNA  * ROMEN GEMINATE_SIGN   * VALA GEMINATE_SIGN    * ANNA GEMINATE_SIGN
     [r * {L6_S}]      --> [ ORE   * {L6_T}] 
-    [r * {L6_S}]{V_D} --> [ ROMEN * {L6_T}]{T_S_D} 
+    [r * {L6_S}]{V_D} --> [ ROMEN * {L6_T}]{_V_D_} 
 
     \** This one is not useful (redundant with higher) **\
     \** Keep it for clarity of mind **\
     r_                --> ORE
 
-    s{V_D}            --> SILME_NUQUERNA {T_S_D}  \** Before a vowel goes down **\
+    s{V_D}            --> SILME_NUQUERNA {_V_D_}  \** Before a vowel goes down **\
     s                 --> SILME                   \** Any other pos, up **\
-    z{V_D}            --> ESSE_NUQUERNA {T_S_D}   \** Before a vowel goes down **\
+    z{V_D}            --> ESSE_NUQUERNA {_V_D_}   \** Before a vowel goes down **\
     z                 --> ESSE                    \** Any other pos, up **\
 
-    h{V_D}            --> HYARMEN {T_XS_D}
+    h{V_D}            --> HYARMEN {_V_D_}
     h                 --> HYARMEN
-    hh{V_D}           --> HYARMEN DASH_INF_L {T_XS_D}
-    hh                --> HYARMEN DASH_INF_L
+    hh{V_D}           --> HYARMEN GEMINATE_SIGN {_V_D_}
+    hh                --> HYARMEN GEMINATE_SIGN
                       
-    l{V_D}            --> LAMBE {T_XL_D}
+    l{V_D}            --> LAMBE {_V_D_}
     l                 --> LAMBE
                       
-    ll{V_D}           --> LAMBE LAMBE_MARK_TILD {T_XL_D}
-    ll                --> LAMBE LAMBE_MARK_TILD
+    ll{V_D}           --> LAMBE GEMINATE_SIGN {_V_D_}
+    ll                --> LAMBE GEMINATE_SIGN
   
   \end
   
@@ -276,3 +260,6 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   
 \end
 
+\beg postprocessor
+  \resolve_virtuals
+\end

data/glaemresources/modes/quenya.glaem

@@ -22,8 +22,6 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 **\
 
-\** Changelog **\
-\**
 \beg changelog
   \entry "0.0.2", "added χ for the word χarina, correcting ts/ps sequences to work better with eldamar"
   \entry "0.0.3", "added o/u curl option"
@@ -37,11 +35,11 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \entry "0.1.1", "Added default option for voiced plosives : use mb, nd, ng, ngw"
   \entry "0.1.2", "Added a tehta shape selection"
   \entry "0.1.3", "Fixing ks, ps, ts. Fixing dot under ore, romen in implicit a mode."
+  \entry "0.1.4", "Conforming to the new csub format. Cleaning with new csub classes."
+  \entry "0.1.5", "csub removed. Now using virtual chars defined in charsets."
 \end
-**\
 
 \**
-  TODO : Use the new csub directive for all diacritics/signs that could have variants (e.g. THINF_DDOT (LAMBE_MARK_DDOT for LAMBE), DASH_INF (LAMBE_MARK_TILD for LAMBE), SHOOK_LEFT)
   TODO : Option for dot or not in 'a implicit' option before long vowels ?
   TODO : bb, dd etc ? (for noobs)
 **\
@@ -49,7 +47,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \language "Quenya"
 \writing  "Tengwar"
 \mode     "Classical"
-\version  "0.1.3"
+\version  "0.1.5"
 \authors  "Talagan (Benjamin Babut)"
 
 \charset  tengwar_ds true
@@ -134,7 +132,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
     \if implicit_a
       {_A_}              === {NULL}
-      {_NVOWEL_}         === THINF_DOT
+      {_NVOWEL_}         === NO_VOWEL
     \else
       {_A_}              === {A_SHAPE}
       {_NVOWEL_}         === {NULL}
@@ -192,20 +190,20 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     {_L1_}        === TINCO * PARMA   * CALMA * QUESSE
 
     \** GEMINATED **\
-    {L1_1_GEMS}   === tt                  * pp               * {K}{K}
-    {_L1_1_GEMS_} === TINCO DASH_INF_S    * PARMA DASH_INF_S * CALMA DASH_INF_S
+    {L1_1_GEMS}   === tt                  * pp                    * {K}{K}
+    {_L1_1_GEMS_} === TINCO GEMINATE_SIGN * PARMA GEMINATE_SIGN   * CALMA GEMINATE_SIGN
 
     \** NORMAL **\
     [ {L1} * {L1_1_GEMS} ] {V_D_WN} --> [ {_L1_} * {_L1_1_GEMS_} ] {_V_D_WN_}
 
     \** OTHERS **\
-    ty{V_D_WN}          --> TINCO THINF_DDOT_L {_V_D_WN_}
-    py{V_D_WN}          --> PARMA THINF_DDOT_L {_V_D_WN_}
+    ty{V_D_WN}          --> TINCO PALATAL_SIGN {_V_D_WN_}
+    py{V_D_WN}          --> PARMA PALATAL_SIGN {_V_D_WN_}
 
-    ts{V_D_WN}          --> TINCO {_V_D_WN_} SHOOK_RIGHT_L
-    ps{V_D_WN}          --> PARMA {_V_D_WN_} SHOOK_RIGHT_L
-    {K}s{V_D_WN}        --> CALMA SHOOK_LEFT_L {_V_D_WN_}   
-    x{V_D_WN}           --> CALMA SHOOK_LEFT_L {_V_D_WN_}   \** render ks for x **\
+    ts{V_D_WN}          --> TINCO {_V_D_WN_} ALVEOLAR_SIGN
+    ps{V_D_WN}          --> PARMA {_V_D_WN_} ALVEOLAR_SIGN
+    {K}s{V_D_WN}        --> CALMA ALVEOLAR_SIGN {_V_D_WN_}   
+    x{V_D_WN}           --> CALMA ALVEOLAR_SIGN {_V_D_WN_}   \** render ks for x **\
 
     \** ===================== **\
     \**     2ND LINE RULES    **\
@@ -217,7 +215,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     [{L2}]{V_D_WN}  --> [{_L2_}]{_V_D_WN_}
 
     \** Palatalized **\
-    ndy{V_D_WN} --> ANDO THINF_DDOT_XL {_V_D_WN_}
+    ndy{V_D_WN} --> ANDO PALATAL_SIGN {_V_D_WN_}
 
     \** Have some rules for d,b,g,gw although there are not theoritically possible, aldudénie e.g needs it **\
     {L2_UN}               === d       * b         * g       * gw
@@ -248,7 +246,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     [{L3}]{V_D_WN}  --> [{_L3_}]{_V_D_WN_}
 
     \** OTHERS **\
-    hy{V_D_WN}      --> HYARMEN THINF_DDOT_L {_V_D_WN_}
+    hy{V_D_WN}      --> HYARMEN PALATAL_SIGN {_V_D_WN_}
 
     \** Override h with vowels (descendent of hy) **\
     _h{V_D}         --> HYARMEN {_V_D_}
@@ -265,7 +263,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     \** NORMAL **\
     [{L4}]{V_D_WN}    --> [{_L4_}]{_V_D_WN_}
     \** OTHERS **\
-    nty{V_D_WN}       --> ANTO THINF_DDOT_XL {_V_D_WN_}
+    nty{V_D_WN}       --> ANTO PALATAL_SIGN {_V_D_WN_}
 
     \** ===================== **\
     \**     5TH LINE RULES    **\
@@ -275,10 +273,10 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
     [{L5}]{V_D_WN}  --> [{_L5_}]{_V_D_WN_}
 
-    ny{V_D_WN}          --> NUMEN THINF_DDOT_XL {_V_D_WN_}
-    nn{V_D_WN}          --> NUMEN DASH_INF_L    {_V_D_WN_}
-    my{V_D_WN}          --> MALTA THINF_DDOT_XL {_V_D_WN_}
-    mm{V_D_WN}          --> MALTA DASH_INF_L    {_V_D_WN_}
+    ny{V_D_WN}          --> NUMEN PALATAL_SIGN {_V_D_WN_}
+    nn{V_D_WN}          --> NUMEN GEMINATE_SIGN   {_V_D_WN_}
+    my{V_D_WN}          --> MALTA PALATAL_SIGN {_V_D_WN_}
+    mm{V_D_WN}          --> MALTA GEMINATE_SIGN   {_V_D_WN_}
 
     \** ===================== **\
     \**     6TH LINE RULES    **\
@@ -291,7 +289,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     \endif
 
     {L6}        === r     * v     * y                   * w
-    {_L6_}      === ROMEN * VALA  * ANNA THINF_DDOT_L   * VILYA
+    {_L6_}      === ROMEN * VALA  * ANNA PALATAL_SIGN   * VILYA
 
     [{L6}]{V_D_WN} --> [{_L6_}]{_V_D_WN_}
 
@@ -301,8 +299,8 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     \** Override rule r + null **\
     r                 --> {_LONE_R_} {_NVOWEL_}
 
-    rr{V_D_WN}        --> ROMEN DASH_INF_S {_V_D_WN_}
-    ry{V_D_WN}        --> ROMEN THINF_DDOT_XS {_V_D_WN_}
+    rr{V_D_WN}        --> ROMEN GEMINATE_SIGN {_V_D_WN_}
+    ry{V_D_WN}        --> ROMEN PALATAL_SIGN {_V_D_WN_}
     rd{V_D_WN}        --> ARDA {_V_D_WN_}
 
     \** ===================== **\
@@ -313,7 +311,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
     [{LINE_L}]{V_D_WN}    --> [{_LINE_L_}]{_V_D_WN_}
 
-    ly{V_D_WN}            --> LAMBE LAMBE_MARK_DDOT {_V_D_WN_}
+    ly{V_D_WN}            --> LAMBE PALATAL_SIGN {_V_D_WN_}
     hl{V_D_WN}            --> HALLA LAMBE {_V_D_WN_}
     hr{V_D_WN}            --> HALLA ROMEN {_V_D_WN_}
 
@@ -405,13 +403,6 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \end
 
 \beg postprocessor
-  \** TODO : Move formen to S, move hyarmen to XS **\
-  \csub A_TEHTA          "A_TEHTA_XS        TELCO ARA"  "A_TEHTA_S         ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN" "A_TEHTA_L         TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN" "A_TEHTA_XL         TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME"
-  \csub A_TEHTA_CIRCUM   "A_TEHTA_CIRCUM_XS TELCO ARA"  "A_TEHTA_CIRCUM_S  ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN" "A_TEHTA_CIRCUM_L  TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN" "A_TEHTA_CIRCUM_XL  TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME"
-  \csub E_TEHTA          "E_TEHTA_XS        TELCO ARA"  "E_TEHTA_S         ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN" "E_TEHTA_L         TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN" "E_TEHTA_XL         TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME"
-  \csub I_TEHTA          "I_TEHTA_XS        TELCO ARA"  "I_TEHTA_S         ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN" "I_TEHTA_L         TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN" "I_TEHTA_XL         TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME"
-  \csub O_TEHTA          "O_TEHTA_XS        TELCO ARA"  "O_TEHTA_S         ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN" "O_TEHTA_L         TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN" "O_TEHTA_XL         TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME"
-  \csub U_TEHTA          "U_TEHTA_XS        TELCO ARA"  "U_TEHTA_S         ORE TW_EXT_11 TW_EXT_12 SULE HYARMEN" "U_TEHTA_L         TINCO CALMA PARMA QUESSE AHA HWESTA LAMBE ALDA YANTA URE ROMEN ARDA SILME_NUQUERNA ESSE_NUQUERNA VALA ANNA VILYA FORMEN" "U_TEHTA_XL         TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME"
-  \csub THINF_DOT        "THINF_DOT_XS      TELCO ROMEN ARDA" "THINF_DOT_L ORE TW_EXT_11 TW_EXT_12  TINCO PARMA SULE FORMEN VALA ANNA VILYA SILME ESSE AHA HWESTA HYARMEN YANTA URE" "THINF_DOT_XL QUESSE CALMA TW_EXT_13 TW_EXT_14 TW_EXT_21 TW_EXT_22 TW_EXT_23 TW_EXT_24 ANDO UMBAR ANGA UNGWE ANTO AMPA ANCA UNQUE NUMEN MALTA NOLDO NWALME" "LAMBE_MARK_DOT LAMBE ALDA"
+  \resolve_virtuals
 \end
 

data/lib/api/charset.rb

@@ -27,39 +27,121 @@ module Glaemscribe
       
       attr_accessor :errors
       attr_reader   :chars
+      attr_reader   :virtual_chars
             
       class Char
         attr_accessor :line
         attr_accessor :code
         attr_accessor :names
         attr_accessor :str
+        attr_accessor :charset
         
         def initialize
           @names = {}
         end
+        
+        def virtual?
+          false
+        end
+      end
+      
+      class VirtualChar
+        attr_accessor :line
+        attr_accessor :names
+        attr_accessor :classes
+        attr_accessor :charset
+        
+        class VirtualClass
+          attr_accessor :target
+          attr_accessor :triggers
+        end
+        
+        def initialize
+          @classes = {} # result_char_1 => [trigger_char_1, trigger_char_2 ...] , result_char_1 => ...
+          @lookup_table = {}
+        end
+        
+        def str
+          VIRTUAL_CHAR_OUTPUT
+        end
+        
+        def finalize
+          @lookup_table = {}
+          @classes.each{ |vc|
+            
+            result_char   = vc.target
+            trigger_chars = vc.triggers
+            
+            trigger_chars.each{ |trigger_char|
+              found = @lookup_table[trigger_char]
+              if found
+                @charset.errors << Glaeml::Error.new(@line, "Trigger char #{trigger_char} found twice in virtual char.")
+              else
+                rc = @charset[result_char]
+                tc = @charset[trigger_char]
+        
+                if rc.nil?
+                  @charset.errors << Glaeml::Error.new(@line, "Trigger char #{trigger_char} points to unknown result char #{result_char}.")
+                elsif tc.nil?
+                  @charset.errors << Glaeml::Error.new(@line, "Unknown trigger char #{trigger_char}.")
+                elsif tc.class == VirtualChar
+                  @charset.errors << Glaeml::Error.new(@line, "Trigger char #{trigger_char} is virtual. This is not supported!")    
+                elsif rc.class == VirtualChar
+                  @charset.errors << Glaeml::Error.new(@line, "Trigger char #{trigger_char} points to another virtual char #{result_char}. This is not supported!")
+                else
+                  tc.names.each{|trigger_char_name| # Don't forget to match all name variants for that trigger char!
+                    @lookup_table[trigger_char_name] = rc
+                  }              
+                end  
+              end              
+            }
+          }
+        end
+        
+        def [](trigger_char_name)
+          @lookup_table[trigger_char_name]
+        end
+        
+        def virtual?
+          true
+        end
       end
       
       def initialize(name)
-        @name   = name
-        @chars  = []
-        @errors = []
+        @name           = name
+        @chars          = []
+        @errors         = []
+        @virtual_chars  = []
       end
       
       # Pass integer (utf8 num) and array (of strings)
       def add_char(line, code, names)
         return if names.empty? || names.include?("?") # Ignore characters with '?'
         
-        c       = Char.new
-        c.line  = line
-        c.code  = code
-        c.names = names
-        c.str   = code.chr('UTF-8')
+        c         = Char.new
+        c.line    = line
+        c.code    = code
+        c.names   = names
+        c.str     = code.chr('UTF-8')
+        c.charset = self
         @chars << c
       end
       
+      def add_virtual_char(line, classes, names)
+        return if names.empty? || names.include?("?") # Ignore characters with '?'
+        
+        c         = VirtualChar.new
+        c.line    = line
+        c.names   = names
+        c.classes = classes # We'll check errors in finalize
+        c.charset = self
+        @chars << c   
+      end
+      
       def finalize
-        @errors = []
-        @lookup_table = {}
+        @errors         = []
+        @lookup_table   = {}
+        @virtual_chars  = []
         
         @chars.each { |c|
           c.names.each { |cname|
@@ -72,6 +154,13 @@ module Glaemscribe
           }
         }
         
+        @chars.each{ |c|
+          if c.class == VirtualChar
+            c.finalize
+            @virtual_chars << c
+          end
+        }
+        
         API::Debug::log("Finalized charset '#{@name}', #{@lookup_table.count} symbols loaded.")
       end
       

data/lib/api/charset_parser.rb

@@ -45,6 +45,19 @@ module Glaemscribe
           names  = char_element.args[1..-1].map{|cname| cname.strip }.reject{ |cname| cname.empty? }
           @charset.add_char(char_element.line,code,names)
         }
+        
+        doc.root_node.gpath("virtual").each { |virtual_element|
+          names   = virtual_element.args
+          classes = []
+          virtual_element.gpath("class").each { |class_element|
+            vc =  Charset::VirtualChar::VirtualClass.new
+            vc.target    = class_element.args[0]
+            vc.triggers  = class_element.args[1..-1].map{|cname| cname.strip }.reject{ |cname| cname.empty? }     
+            classes << vc
+          }
+          @charset.add_virtual_char(virtual_element.line,classes,names)
+        }
+        
         @charset.finalize
              
         @charset 

data/lib/api/constants.rb

@@ -25,5 +25,6 @@ module Glaemscribe
     WORD_BREAKER        = "|"
     WORD_BOUNDARY       = "_"
     UNKNOWN_CHAR_OUTPUT = "☠"      
+    VIRTUAL_CHAR_OUTPUT = "☢" # When transcribing a virtual char...
   end
 end

data/lib/api/glaeml.rb

@@ -67,6 +67,13 @@ module Glaemscribe
           @children     = []
         end
         
+        # Make our object clonable
+        def initialize_copy(other)
+          super
+          @args = other.args.clone
+          @children = other.children.map{|c| c.clone}
+        end
+        
         def pathfind_crawl(apath, found)
         
           children.each{ |c|

data/lib/api/mode_parser.rb

@@ -181,7 +181,7 @@ module Glaemscribe
           if !operator_class
             @mode.errors << Glaeml::Error.new(element.line,"Operator #{operator_name} is unknown.")
           else            
-            term.operators << operator_class.new(element.args.clone)
+            term.operators << operator_class.new(element.clone)
           end  
         }  
         

data/lib/api/post_processor/resolve_virtuals.rb

@@ -0,0 +1,75 @@
+# 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 ResolveVirtualsPostProcessorOperator < PostProcessorOperator
+      
+      def finalize(trans_options)
+        super(trans_options)
+        @last_triggers = {} # Allocate the lookup here to optimize
+      end
+      
+      def reset_trigger_states(charset)
+        # For each virtual char in charset, maintain a state.
+        charset.virtual_chars.each{ |vc|
+          @last_triggers[vc] = nil # Clear the state
+        }
+      end
+      
+      def apply(tokens,charset)
+        
+        reset_trigger_states(charset)
+        
+        tokens.each_with_index{ |token,idx|
+          
+          if token == '*SPACE'
+            reset_trigger_states(charset)
+            next
+          end
+          
+          # Check if token is a virtual char
+          c = charset[token]
+          next if c.nil? # May happen for empty tokens
+          if c.virtual?
+            # Try to replace
+            last_trigger = @last_triggers[c]
+            if last_trigger != nil
+              tokens[idx] = last_trigger.names.first # Take the first name of the non-virtual replacement.
+            end
+          else
+            # Update states of virtual classes
+            charset.virtual_chars.each{|vc|
+              rc                  = vc[token]
+              @last_triggers[vc]  = rc if rc != nil 
+            }
+          end
+        }
+        tokens
+      end
+    end
+
+    ResourceManager::register_post_processor_class("resolve_virtuals", ResolveVirtualsPostProcessorOperator)    
+
+  end
+end

data/lib/api/post_processor/reverse.rb

@@ -24,7 +24,7 @@ module Glaemscribe
   module API
 
     class ReversePostProcessorOperator < PostProcessorOperator
-      def apply(tokens)
+      def apply(tokens,charset)
         tokens.reverse
       end
     end

data/lib/api/pre_processor/elvish_numbers.rb

@@ -26,10 +26,10 @@ module Glaemscribe
     class ElvishNumbersPreProcessorOperator < PreProcessorOperator
 
       def apply(l)
-        base    = args[0]
+        base    = finalized_glaeml_element.args[0]
         base    = (base)?(base.to_i):(12)
         
-        reverse = args[1]
+        reverse = finalized_glaeml_element.args[1]
         reverse = (reverse != nil)?(reverse == "true" || reverse == true):(true) 
 
         l.gsub(/\d+/) { |f| 

data/lib/api/pre_processor/rxsubstitute.rb

@@ -27,8 +27,8 @@ module Glaemscribe
     class RxSubstitutePreProcessorOperator < PreProcessorOperator
 
       def apply(l)
-        what = /#{@args[0]}/
-        with = @args[1]
+        what = /#{finalized_glaeml_element.args[0]}/
+        with = finalized_glaeml_element.args[1]
         l.gsub(what, with)
       end
       

data/lib/api/pre_processor/substitute.rb

@@ -26,8 +26,8 @@ module Glaemscribe
     class SubstitutePreProcessorOperator < PreProcessorOperator
       
       def apply(l)
-        what = @args[0]
-        with = @args[1]
+        what = finalized_glaeml_element.args[0]
+        with = finalized_glaeml_element.args[1]
         l.gsub(what, with)
       end
     end

data/lib/api/pre_processor/up_down_tehta_split.rb

@@ -26,11 +26,11 @@ module Glaemscribe
     class UpDownTehtaSplitPreProcessorOperator < PreProcessorOperator
            
       attr_reader :vowel_list, :consonant_list
-      def initialize(args)
-        super(args)
+      def finalize(trans_options)
+        super(trans_options)
         
-        vowel_list          = args[0]
-        consonant_list      = args[1]
+        vowel_list          = finalized_glaeml_element.args[0]
+        consonant_list      = finalized_glaeml_element.args[1]
             
         vowel_list          = vowel_list.split(/,/).map{|s| s.strip}
         consonant_list      = consonant_list.split(/,/).map{|s| s.strip}  

data/lib/api/transcription_pre_post_processor.rb

@@ -24,11 +24,11 @@ module Glaemscribe
   module API
     
     class PrePostProcessorOperator
-      attr_reader :args
-      attr_reader :raw_args
+      attr_reader :glaeml_element
+      attr_reader :finalized_glaeml_element
       
-      def initialize(raw_args)
-        @raw_args = raw_args
+      def initialize(glaeml_element)
+        @glaeml_element = glaeml_element
       end
       
       def eval_arg(arg, trans_options)
@@ -40,11 +40,16 @@ module Glaemscribe
         return arg 
       end
       
-      def finalize(trans_options)
-        @args = []
-        @raw_args.each{ |arg|
-          @args << eval_arg(arg, trans_options)
+      def finalize_glaeml_element(ge, trans_options)
+        ge.args.map! { |arg| eval_arg(arg, trans_options) }
+        ge.children.each{ |child|
+          finalize_glaeml_element(child, trans_options)
         }
+        ge
+      end
+      
+      def finalize(trans_options)
+        @finalized_glaeml_element = finalize_glaeml_element(@glaeml_element.clone, trans_options)
       end
       
       def apply
@@ -122,7 +127,7 @@ module Glaemscribe
          
         # Apply filters
         @operators.each{ |operator|
-          tokens = operator.apply(tokens)
+          tokens = operator.apply(tokens,out_charset)
         } 
         
         # Convert output

data/lib/glaemscribe.rb

@@ -65,7 +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"
+    require API_PATH + "/api/post_processor/resolve_virtuals.rb"
     
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: glaemscribe
 version: !ruby/object:Gem::Version
-  version: 1.0.15
+  version: 1.0.16
 platform: ruby
 authors:
 - Benjamin 'Talagan' Babut
@@ -72,7 +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/resolve_virtuals.rb
 - lib/api/post_processor/reverse.rb
 - lib/api/pre_processor/downcase.rb
 - lib/api/pre_processor/elvish_numbers.rb
@@ -110,7 +110,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.1
+rubygems_version: 2.4.8
 signing_key: 
 specification_version: 4
 summary: Glǽmscribe

data/lib/api/post_processor/csub.rb

@@ -1,64 +0,0 @@
-# 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