glaemscribe 1.1.2 → 1.1.3

data/glaemresources/modes/raw-tengwar.glaem

@@ -0,0 +1,234 @@
+\**
+
+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/>.
+
+**\
+
+\beg changelog
+  \entry "0.0.1" "Initial version."
+\end
+
+\language "Raw Tengwar"
+\writing  "Tengwar"
+\mode     "Raw"
+\version  "0.0.1"
+\authors  "Talagan (Benjamin Babut)"
+
+\metamode true
+
+\charset  tengwar_ds_sindarin true
+\charset  tengwar_ds_parmaite false
+\charset  tengwar_ds_eldamar  false
+\charset  tengwar_ds_annatar  false
+\charset  tengwar_ds_elfica   false
+\charset  tengwar_freemono    false
+
+
+\beg      options
+  \beg option consonant_modification_style CONSONANT_MODIFICATION_STYLE_BAR
+    \value CONSONANT_MODIFICATION_STYLE_WAVE 0
+    \value CONSONANT_MODIFICATION_STYLE_BAR 1
+  \end
+\end
+
+\beg      preprocessor
+  \** Work exclusively downcase **\
+  \downcase
+\end
+
+
+\beg processor
+
+  \beg    rules litteral
+	
+    \if "consonant_modification_style == CONSONANT_MODIFICATION_STYLE_WAVE"
+      {GEMINATE} === GEMINATE_SIGN_TILD
+      {NASAL}    === NASALIZE_SIGN_TILD
+    \else
+      {GEMINATE} === GEMINATE_SIGN
+      {NASAL}    === NASALIZE_SIGN
+    \endif
+		
+    _a_      --> A_TEHTA
+		_acirc_  --> A_TEHTA_CIRCUM
+    _arev_   --> A_TEHTA_REVERSED
+
+    _e_      --> E_TEHTA
+    _i_      --> I_TEHTA
+    _o_      --> O_TEHTA
+    _u_      --> U_TEHTA
+    
+    _a<_     --> A_TEHTA_INF
+    _e<_     --> E_TEHTA_INF
+    _i<_     --> I_TEHTA_INF
+    _o<_     --> O_TEHTA_INF
+    _u<_     --> U_TEHTA_INF
+    
+    _unutixe_ --> I_TEHTA_INF
+		
+    _ee_    --> E_TEHTA_DOUBLE
+    _ii_    --> I_TEHTA_DOUBLE
+    _oo_    --> O_TEHTA_DOUBLE
+    _uu_    --> U_TEHTA_DOUBLE
+    
+    _ee<_    --> E_TEHTA_DOUBLE_INF
+    _ii<_    --> I_TEHTA_DOUBLE_INF
+
+    _(tinco,tw11)_   --> TINCO
+		_(parma,tw12)_   --> PARMA
+		_(calma,tw13)_   --> CALMA
+		_(quesse,tw14)_  --> QUESSE
+
+    _(ando,tw21)_    --> ANDO
+		_(umbar,tw22)_   --> UMBAR
+		_(anga,tw23)_    --> ANGA
+		_(ungwe,tw24)_   --> UNGWE
+		
+		_(sule,súle,thule,thúle,tw31)_    --> SULE
+		_(formen,tw32)_                   --> FORMEN
+		_(aha,harma,tw33)_                --> AHA
+		_(hwesta,tw34)_                   --> HWESTA
+		
+		_(anto,tw41)_   --> ANTO
+		_(ampa,tw42)_   --> AMPA
+		_(anca,tw43)_   --> ANCA
+		_(unque,tw44)_  --> UNQUE
+		
+		_(numen,númen,tw51)_     --> NUMEN
+		_(malta,tw52)_           --> MALTA
+		_(noldo,ñoldo,tw53)_     --> NOLDO
+		_(nwalme,ñwalme,tw54)_   --> NWALME
+		
+		_(ore,óre,tw61)_          --> ORE
+		_(vala,tw62)_             --> VALA
+		_(anna,tw63)_             --> ANNA
+		_(vilya,wilya,tw64)_      --> VILYA	
+		
+		_(romen,rómen,tw71)_      --> ROMEN
+		_(arda,tw72)_             --> ARDA
+		_(lambe,tw73)_            --> LAMBE
+		_(alda,tw74)_             --> ALDA
+		
+		_(silme,tw81)_                  --> SILME
+		_(silmenuquerna,silmen,tw82)_   --> SILME_NUQUERNA
+		_(esse,tw83)_                   --> ESSE
+		_(essenuquerna,essen,tw84)_     --> ESSE_NUQUERNA
+		
+		_(hyarmen,tw91)_                   --> HYARMEN
+		_(hwestasindarinwa,hwestas,tw92)_  --> HWESTA_SINDARINWA
+		_(yanta,tw93)_                     --> YANTA
+		_(ure,úre,tw94)_                   --> URE
+		
+    
+		_(osse)_  --> OSSE
+		_(halla)_ --> HALLA
+	  _(vaia,vaiya)_  --> VAIA
+    
+    
+    _(mh)_                --> TW_MH
+    _(mhbeleriandic,mhb)_ --> TW_MH_BELERIANDIC
+    _(hwlowdham,hwl)_     --> TW_HW_LOWDHAM
+    
+		
+		\** ligatures **\
+    _(harmasilme,ahasilme,silmeharma,silmeaha)_ --> ANCA_CLOSED
+    _(hwestatinco,tincohwesta)_                 --> HWESTA_TINCO
+    _(harmatinco,ahatinco,tincoharma,tincoaha)_ --> AHA_TINCO
+    
+    _(telco)_   --> TELCO
+		_(ara,ára)_ --> ARA
+		
+		_(geminate)_  --> {GEMINATE}
+		_(nasal)_     --> {NASAL}
+		_(palatal)_   --> PALATAL_SIGN
+		
+		_0_ --> NUM_0
+    _1_ --> NUM_1
+    _2_ --> NUM_2
+    _3_ --> NUM_3
+    _4_ --> NUM_4
+    _5_ --> NUM_5
+    _6_ --> NUM_6
+    _7_ --> NUM_7
+    _8_ --> NUM_8
+    _9_ --> NUM_9
+    _10_ --> NUM_10
+    _11_ --> NUM_11
+    
+  \end
+
+  \beg    rules punctuation
+	  / --> {NULL}
+	
+    . --> PUNCT_DDOT
+    .. --> PUNCT_DOT PUNCT_DDOT PUNCT_DOT
+    …  --> PUNCT_TILD
+    ... --> PUNCT_TILD
+    .... --> PUNCT_TILD
+    ..... --> PUNCT_TILD
+    ...... --> PUNCT_TILD
+    ....... --> PUNCT_TILD
+
+    , --> PUNCT_DOT
+    : --> PUNCT_DOT
+    ; --> PUNCT_DOT
+    ! --> PUNCT_EXCLAM
+    ? --> PUNCT_INTERR
+    · --> PUNCT_DOT
+
+    \** Apostrophe **\
+
+    ' --> {NULL}
+    ’ --> {NULL}
+
+    \** Quotes **\
+
+    “ --> DQUOT_OPEN
+    ” --> DQUOT_CLOSE
+    « --> DQUOT_OPEN
+    » --> DQUOT_CLOSE
+
+    - --> {NULL}
+    – --> PUNCT_TILD
+    — --> PUNCT_TILD
+
+    [ --> PUNCT_PAREN_L
+    ] --> PUNCT_PAREN_R
+    ( --> PUNCT_PAREN_L
+    ) --> PUNCT_PAREN_R
+    { --> PUNCT_PAREN_L
+    } --> PUNCT_PAREN_R
+\**    < --> PUNCT_PAREN_L : cannot be used since it is already used as a letter in group litteral **\
+\**    > --> PUNCT_PAREN_R : cannot be used since it is already used as a letter in group litteral **\
+
+    \** Not universal between fonts ... **\
+    $ --> BOOKMARK_SIGN
+    ≤ --> RING_MARK_L \** Ring inscription left beautiful stuff **\
+    ≥ --> RING_MARK_R \** Ring inscription right beautiful stuff **\
+
+  \end
+
+\end
+
+\beg postprocessor
+  \resolve_virtuals
+\end
+

data/glaemresources/modes/rlyehian.glaem

@@ -30,18 +30,22 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 \**  R'lyehian mode for glaemscribe : a non-euclidian joke, muhahahaha **\
 
-\language "R'lyehian"
-\writing  Tengwar
-\mode     Glaemscrafu
-\version  0.0.3
-\authors  "H.P.Lovecraft & The Great Ancient Gods, impl. Fthalagn"
-
 \beg changelog
   \entry "0.0.1" "First version"
-	\entry 0.0.2 "Ported to virtual chars"
-	\entry 0.0.3 "Ported to various charsets"
+	\entry "0.0.2" "Ported to virtual chars"
+	\entry "0.0.3" "Ported to various charsets"
+  \entry "0.1.1" "Added support for inlined raw tengwar"
 \end
 
+
+\language "R'lyehian"
+\writing  "Tengwar"
+\mode     "Glaemscrafu"
+\version  "0.1.1"
+\authors  "H.P.Lovecraft & The Great Ancient Gods, impl. Fthalagn"
+
+\raw_mode "raw-tengwar"
+
 \charset  tengwar_ds_sindarin true
 \charset  tengwar_ds_parmaite false
 \charset  tengwar_ds_eldamar  false

data/glaemresources/modes/sindarin-beleriand.glaem

@@ -30,14 +30,17 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \entry "0.0.5" "Added charset support for Annatar"
   \entry "0.0.6" "Added support for the FreeMonoTengwar font"
   \entry "0.1.0" "Added support for the Tengwar Elfica font"
+  \entry "0.1.1" "Added support for inlined raw tengwar"
 \end
 
 \language "Sindarin"
 \writing  "Tengwar"
 \mode     "Beleriand"
-\version  "0.1.0"
+\version  "0.1.1"
 \authors  "J.R.R. Tolkien, impl. Talagan (Benjamin Babut)"
 
+\raw_mode "raw-tengwar"
+
 \charset  tengwar_ds_sindarin true
 \charset  tengwar_ds_parmaite false
 \charset  tengwar_ds_eldamar  false

data/glaemresources/modes/sindarin.glaem

@@ -33,15 +33,17 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \entry "0.0.7" "Added charset support for Annatar"
   \entry "0.0.8" "Added support for the FreeMonoTengwar font" 
   \entry "0.1.0" "Added support for the Tengwar Elfica font"
+  \entry "0.1.1" "Added support for inlined raw tengwar"  
 \end
 
-
 \language "Sindarin"
 \writing  "Tengwar"
 \mode     "General Use"
-\version  "0.1.0"
+\version  "0.1.1"
 \authors  "J.R.R. Tolkien, impl. Talagan (Benjamin Babut)"
 
+\raw_mode "raw-tengwar"
+
 \charset  tengwar_ds_sindarin true
 \charset  tengwar_ds_parmaite false
 \charset  tengwar_ds_eldamar  false

data/glaemresources/modes/telerin.glaem

@@ -31,14 +31,17 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \entry "0.0.5" "Added support for the FreeMonoTengwar font" 
   \entry "0.0.6" "Ported some options from the quenya mode"
   \entry "0.1.0" "Added support for the Tengwar Elfica font"
+  \entry "0.1.1" "Added support for inlined raw tengwar"  
 \end
 
 \language "Telerin"
 \writing  "Tengwar"
 \mode     "Glaemscrafu"
-\version  "0.1.0"
+\version  "0.1.1"
 \authors  "Talagan (Benjamin Babut), based on J.R.R Tolkien"
 
+\raw_mode "raw-tengwar"
+
 \charset  tengwar_ds_sindarin true
 \charset  tengwar_ds_parmaite false
 \charset  tengwar_ds_eldamar  false

data/glaemresources/modes/westron.glaem

@@ -28,15 +28,18 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \entry "0.0.4" "Added charset support for Annatar"
   \entry "0.0.5" "Added support for the FreeMonoTengwar font" 
   \entry "0.1.0" "Added support for the Tengwar Elfica font"
+  \entry "0.1.1" "Added support for inlined raw tengwar"  
 \end
 
 \**  Westron mode for glaemscribe (MAY BE INCOMPLETE) **\
 \language Westron
 \writing  Tengwar
 \mode     Glaemscrafu
-\version  "0.1.0"
+\version  "0.1.1"
 \authors  "Talagan (Benjamin Babut), based on J.R.R. Tolkien"
 
+\raw_mode "raw-tengwar"
+
 \charset  tengwar_ds_sindarin true
 \charset  tengwar_ds_parmaite false
 \charset  tengwar_ds_eldamar  false

data/glaemresources/modes/westsaxon.glaem

@@ -23,15 +23,18 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 **\
 
 \beg changelog
-  \entry 0.0.2 "Porting to virtual chars"
+  \entry "0.0.2" "Porting to virtual chars"
+  \entry "0.1.1" "Added support for inlined raw tengwar"  
 \end
 
 \language "Old English"
 \writing  "Tengwar"
 \mode     "West Saxon"
-\version  "0.1.0"
+\version  "0.1.1"
 \authors  "J.R.R. Tolkien, impl. Talagan (Benjamin Babut)"
 
+\raw_mode "raw-tengwar"
+
 \charset  tengwar_ds_eldamar true
 \** Other charsets cannot handle all diacritics we are using here ... **\
 
@@ -238,10 +241,10 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     \** ## Liquids **\
     \** ## **\
 
-    {S_VOWELS_WN}w{S_VOWELS_WN}   --> 2,1,3 --> ROMEN {_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
-    {S_VOWELS_WN}ww                   --> 2,1   --> ROMEN GEMINATE_DOUBLE {_S_VOWELS_UP_WN_}
-    {S_VOWELS_WN}[l * ll]             --> 2,1   --> [LAMBE * LAMBE GEMINATE_DOUBLE]{_S_VOWELS_UP_WN_}
-    {S_VOWELS_WN}ld                   --> 2,1   --> ALDA {_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}w{S_VOWELS_WN}             --> ROMEN {_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
+    {S_VOWELS_WN}ww                         --> ROMEN GEMINATE_DOUBLE {_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}[l * ll]         --> 2,1   --> [LAMBE * LAMBE GEMINATE_DOUBLE]{_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}ld                         --> ALDA {_S_VOWELS_UP_WN_}
 
 
     \** ## Alveolar (sifflantes) **\
@@ -252,40 +255,36 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     {L8_IMG_GEMS} ===  SILME_NUQUERNA GEMINATE_DOUBLE * ESSE_NUQUERNA GEMINATE_DOUBLE
     
     {S_VOWELS_WN}[{L8_KER}]{S_VOWELS_WN}  --> 2,1,3 --> [{L8_IMG}]{_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
-    {S_VOWELS_WN}[{L8_KER_GEMS}]              --> 2,1   --> [{L8_IMG_GEMS}]{_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}[{L8_KER_GEMS}]          --> 2,1   --> [{L8_IMG_GEMS}]{_S_VOWELS_UP_WN_}
 
 
     \** ## FINAL S (Challenging!) **\
     {S_VOWELS_WN}s_                               --> SHOOK_BEAUTIFUL {_S_VOWELS_UP_WN_} \** # Final rule for s **\
     _{S_VOWELS_WN}s_                              --> SILME_NUQUERNA {_S_VOWELS_UP_WN_} \** # Rule _es_ **\
-    [{L_VOWELS} * _ ]{S_VOWELS_WN}s_              --> 2,1,3     --> [{L_TEHTAR} * {NULL} ] SILME_NUQUERNA {_S_VOWELS_UP_WN_} \** # Rule for éis_, és_ **\
-    {NULL}[ {S_VOWELS_NP_KERNEL} ]{S_VOWELS}s_    --> 1,3,2,4   --> TELCO [ {TEHTAR_UP_NP} ] SILME_NUQUERNA {_S_VOWELS_UP_} \** # Rule for ies_   **\
+    [{L_VOWELS} * _ ]{S_VOWELS_WN}s_              --> [{L_TEHTAR} * {NULL} ] SILME_NUQUERNA {_S_VOWELS_UP_WN_} \** # Rule for éis_, és_ **\
+    {NULL}[ {S_VOWELS_NP_KERNEL} ]{S_VOWELS}s_    --> TELCO [ {TEHTAR_UP_NP} ] SILME_NUQUERNA {_S_VOWELS_UP_} \** # Rule for ies_   **\
 
     s --> SILME \** # Overload lonely s **\
     z --> ESSE  \** # Overload lonely z **\
 
     \** ## Ligatures **\
     \** ## **\
-    {LINE_VARIOUS_1_KER}      ===  sċ 
-    {LINE_VARIOUS_1_IMG}      ===  ANCA_CLOSED  
-    {LINE_VARIOUS_2_KER}      ===  hw * çt * (χt,ħt)
-    {LINE_VARIOUS_2_IMG}      ===  HARP_SHAPED  * AHA_TINCO  * HWESTA_TINCO 
-
-    {S_VOWELS_WN}[{LINE_VARIOUS_1_KER}]{S_VOWELS_WN} --> 2,1,3 --> [{LINE_VARIOUS_1_IMG}]{_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
-    {S_VOWELS_WN}[{LINE_VARIOUS_2_KER}]{S_VOWELS_WN} --> 2,1,3 --> [{LINE_VARIOUS_2_IMG}]{_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
-
-
+    {LINE_VARIOUS_KER}      ===  sċ * hw * çt * (χt,ħt)
+    {LINE_VARIOUS_IMG}      ===  ANCA_CLOSED * HARP_SHAPED  * AHA_TINCO  * HWESTA_TINCO 
+ 
+    {S_VOWELS_WN}[{LINE_VARIOUS_KER}]{S_VOWELS_WN} --> 2,1,3 --> [{LINE_VARIOUS_IMG}]{_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
+  
     \** ## Various **\
     \** ## **\
-    {S_VOWELS_WN}h{S_VOWELS_WN}   --> 2,1,3 --> HYARMEN {_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
-    {S_VOWELS_WN}hh               --> 2,1   --> HYARMEN GEMINATE_DOUBLE {_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}h{S_VOWELS_WN}   --> HYARMEN {_S_VOWELS_UP_WN_}{_S_VOWELS_DN_WN_}
+    {S_VOWELS_WN}hh               --> HYARMEN GEMINATE_DOUBLE {_S_VOWELS_UP_WN_}
 
 
     \** ## X **\
     \** ## For x, due to the cedilla, we cannot put tehtas under the tengwa. **\
-    {S_VOWELS_WN}x  --> 2,1 --> QUESSE SHOOK_LEFT_L {_S_VOWELS_UP_WN_}
-    {S_VOWELS_WN}xx --> 2,1 --> QUESSE SHOOK_LEFT_L GEMINATE_DOUBLE {_S_VOWELS_UP_WN_}
-    {S_VOWELS_WN}nx --> 2,1 --> QUESSE SHOOK_LEFT_L TILD_SUP_S {_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}x  --> QUESSE SHOOK_LEFT_L {_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}xx --> QUESSE SHOOK_LEFT_L GEMINATE_DOUBLE {_S_VOWELS_UP_WN_}
+    {S_VOWELS_WN}nx --> QUESSE SHOOK_LEFT_L TILD_SUP_S {_S_VOWELS_UP_WN_}
   \end
   
   \beg rules punctuation 

data/lib/api/mode.rb

@@ -37,6 +37,8 @@ module Glaemscribe
       attr_accessor :supported_charsets
       attr_accessor :default_charset
       
+      attr_accessor :raw_mode_name # Read from glaeml
+      
       attr_reader   :latest_option_values
          
       def initialize(name)
@@ -111,24 +113,61 @@ module Glaemscribe
         @pre_processor.finalize(@latest_option_values)
         @post_processor.finalize(@latest_option_values)
         @processor.finalize(@latest_option_values)
-        
+    
+        raw_mode.finalize options if raw_mode
+          
         self
       end
       
-      def transcribe(content, charset = nil)
+      def raw_mode
+        return @raw_mode if @raw_mode
+        loaded_raw_mode = (@raw_mode_name && Glaemscribe::API::ResourceManager.loaded_modes[@raw_mode_name])    
+        return nil if !loaded_raw_mode
+        @raw_mode = loaded_raw_mode.deep_clone
+      end
+      
+      def strict_transcribe(content, charset = nil)
         charset = default_charset if !charset
         return false, "*** No charset usable for transcription. Failed!" if !charset
   
+        # Parser works line by line
         ret = content.lines.map{ |l| 
-          l = l.strip # Clean the lines
+          restore_lf = false
+          if l[-1] == "\n"
+            l[-1] = "" 
+            restore_lf = true
+          end
           l = @pre_processor.apply(l)
           l = @processor.apply(l)
           l = @post_processor.apply(l, charset)
-        }.join("\n")
-        
+          l += "\n" if restore_lf
+          l
+        }.join
         return true, ret
       end
       
+      def transcribe(content, charset = nil)
+        if raw_mode
+          chunks = content.split(/({{.*?}})/m)
+          ret = ''
+          res = true
+          chunks.each{ |c|
+            if c =~ /{{(.*?)}}/m
+              succ, r = raw_mode.strict_transcribe($1,charset)
+              res = res && succ
+              ret += r if succ
+            else
+              succ, r = strict_transcribe(c,charset)
+              res = res && succ
+              ret += r if succ
+            end
+          }
+          return res,ret
+        else
+          strict_transcribe(content,charset)
+        end
+      end
+      
     end
   end
 end