glaemscribe 1.1.14 → 1.3.0

data/glaemresources/modes/raw-cirth.glaem

@@ -0,0 +1,154 @@
+\**
+
+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/>.
+
+**\
+
+\** very limited mode, mainly used for writing some doc for glaemscribe. **\
+
+\beg changelog
+  \entry "0.0.1" "Initial version."
+\end
+
+\language "Raw Cirth"
+\writing  "Cirth"
+\mode     "Raw Cirth"
+\version  "0.0.1"
+\authors  "Talagan (Benjamin Babut)"
+
+\world      arda
+\invention  experimental
+
+\metamode true
+
+\charset  cirth_ds true
+
+\beg      preprocessor
+  \** Work exclusively downcase **\
+  \downcase
+\end
+
+\beg processor
+
+  \beg    rules litteral
+    _c1_ --> CIRTH_1
+    _c2_ --> CIRTH_2
+    _c3_ --> CIRTH_3
+    _c4_ --> CIRTH_4
+    _c5_ --> CIRTH_5
+    _c6_ --> CIRTH_6
+    _c7_ --> CIRTH_7
+    _c8_ --> CIRTH_8
+    _c9_ --> CIRTH_9
+    _c10_ --> CIRTH_10
+    _c11_ --> CIRTH_11
+    _c12_ --> CIRTH_12
+    _c13_ --> CIRTH_13
+    _c14_ --> CIRTH_14
+    _c15_ --> CIRTH_15
+    _c16_ --> CIRTH_16
+    _c17_ --> CIRTH_17
+    _c18_ --> CIRTH_18
+    _c19_ --> CIRTH_19
+    _c20_ --> CIRTH_20
+    _c21_ --> CIRTH_21
+    _c22_ --> CIRTH_22
+    _c23_ --> CIRTH_23
+    _c24_ --> CIRTH_24
+    _c25_ --> CIRTH_25
+    _c26_ --> CIRTH_26
+    _c27_ --> CIRTH_27
+    _c28_ --> CIRTH_28
+    _c29_ --> CIRTH_29
+    _c30_ --> CIRTH_30
+    _c31_ --> CIRTH_31
+    _c32_ --> CIRTH_32
+    _c33_ --> CIRTH_33
+    _c34_ --> CIRTH_34
+    _c35_ --> CIRTH_35
+    _c36_ --> CIRTH_36
+    _c37_ --> CIRTH_37
+    _c38_ --> CIRTH_38
+    _c39_ --> CIRTH_39
+    _c40_ --> CIRTH_40
+    _c41_ --> CIRTH_41
+    _c42_ --> CIRTH_42
+    _c43_ --> CIRTH_43
+    _c44_ --> CIRTH_44
+    _c45_ --> CIRTH_45
+    _c46_ --> CIRTH_46
+    _c47_ --> CIRTH_47
+    _c48_ --> CIRTH_48
+    _c49_ --> CIRTH_49
+    _c50_ --> CIRTH_50
+    _c51_ --> CIRTH_51
+    _c52_ --> CIRTH_52
+    _c53_ --> CIRTH_53
+    _c54_ --> CIRTH_54
+    _c55_ --> CIRTH_55
+    _c56_ --> CIRTH_56
+    _c57_ --> CIRTH_57
+    _c58_ --> CIRTH_58
+    _c59_ --> CIRTH_59
+    _c60_ --> CIRTH_60
+
+    _c38alt_ --> CIRTH_38_ALT
+    _c45alt_ --> CIRTH_45_ALT
+    _c51alt_ --> CIRTH_51_ALT
+    _c52alt_ --> CIRTH_52_ALT
+    _c55alt_ --> CIRTH_55_ALT
+    _c56alt_ --> CIRTH_56_ALT
+
+    _ce1_ --> CIRTH_EREB_1
+    _ce2_ --> CIRTH_EREB_2
+    _ce3_ --> CIRTH_EREB_3
+    _ce4_ --> CIRTH_EREB_4
+    _ce5_ --> CIRTH_EREB_5
+    _ce6_ --> CIRTH_EREB_6
+    _ce7_ --> CIRTH_EREB_7
+
+    _1_ --> CIRTH_NUMERAL_1
+    _2_ --> CIRTH_NUMERAL_2
+    _3_ --> CIRTH_NUMERAL_3
+    _4_ --> CIRTH_NUMERAL_4
+    _5_ --> CIRTH_NUMERAL_5
+
+    _{UNDERSCORE}_   --> TEHTA_UNDERLINE
+    _sdot_           --> TEHTA_SUB_DOT
+    _(^,circ)_       --> TEHTA_CIRCUM
+
+    {NBSP}           --> NBSP
+  \end
+
+  \beg rules punctuation
+    , --> CIRTH_PUNCT_DOT
+    . --> CIRTH_PUNCT_MID_DOT
+    (..,:) --> CIRTH_PUNCT_TWO_DOTS
+    ... --> CIRTH_PUNCT_THREE_DOTS
+    (....,::) --> CIRTH_PUNCT_FOUR_DOTS
+  \end
+
+\end
+
+\beg postprocessor
+  \resolve_virtuals
+\end
+

data/glaemresources/modes/raw-tengwar.glaem

@@ -25,13 +25,16 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \beg changelog
   \entry "0.0.1" "Initial version."
   \entry "0.0.2" "Added missing extended tengwar."
-  \entry "0.0.3" "Added support for non-breaking spaces"     
+  \entry "0.0.3" "Added support for non-breaking spaces"  
+  \entry "0.0.4" "Added support for new unicode charsets"  
+  \entry "0.0.5" "Added support for the Tengwar Telcontar font"
+  \entry "0.0.6" "Added support for Bombadil W/HW"
 \end
 
 \language "Raw Tengwar"
 \writing  "Tengwar"
 \mode     "Raw Tengwar"
-\version  "0.0.3"
+\version  "0.0.6"
 \authors  "Talagan (Benjamin Babut)"
 
 \world      arda
@@ -44,7 +47,15 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \charset  tengwar_ds_eldamar  false
 \charset  tengwar_ds_annatar  false
 \charset  tengwar_ds_elfica   false
+
+\charset  tengwar_guni_sindarin false
+\charset  tengwar_guni_parmaite false
+\charset  tengwar_guni_eldamar  false
+\charset  tengwar_guni_annatar  false
+\charset  tengwar_guni_elfica   false
+
 \charset  tengwar_freemono    false
+\charset  tengwar_telcontar   false
 
 
 \beg      options
@@ -164,6 +175,8 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     _(mh)_                --> TW_MH
     _(mhbeleriandic,mhb)_ --> TW_MH_BELERIANDIC
     _(hwlowdham,hwl)_     --> TW_HW_LOWDHAM
+    _(hwbombadil,hwbom)_  --> BOMBADIL_HW
+    _(wbombadil,wbom)_    --> BOMBADIL_W
 
     \** ligatures **\
     _(harmasilme,ahasilme,silmeharma,silmeaha)_ --> ANCA_CLOSED
@@ -179,7 +192,11 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     _(geminate)_  --> {GEMINATE}
     _(nasal)_     --> {NASAL}
     _(palatal)_   --> PALATAL_SIGN
-    _(labial)_    --> SEV_TEHTA 
+    _(labial)_    --> WA_TEHTA 
+    
+    \** SA-Rincer to be enhanced ... **\
+    _(sarince)_           --> SARINCE
+    _(arrince,sarincef)_  --> SARINCE_FLOURISHED
  
     _0_ --> NUM_0
     _1_ --> NUM_1
@@ -193,32 +210,42 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     _9_ --> NUM_9
     _10_ --> NUM_10
     _11_ --> NUM_11
+    _12_ --> NUM_12
     
     _(lsd)_ --> CIRC_TEHTA_INF
 
   \end
 
   \beg    rules punctuation
+    
+    \** Allow / as word breaker **\
     / --> {NULL}
+    - --> {NULL}
+
+    ·   --> PUNCT_DOT
+    ,   --> PUNCT_DOT
+    :   --> PUNCT_DOT
+    ;   --> PUNCT_DOT
 
-    . --> PUNCT_DDOT
-    .. --> PUNCT_DOT PUNCT_DDOT PUNCT_DOT
+    .   --> PUNCT_DDOT
+    ..  --> PUNCT_DDOT
+    
+    ...   --> PUSTA_3
+    ....  --> PUSTA_4
+    
+    ::    --> PUSTA_4_SQUARED
+    \** PUSTA_4_HALFED ? **\
+    
+    ..... --> PUSTA_5
+    
     …  --> PUNCT_TILD
-    ... --> PUNCT_TILD
-    .... --> PUNCT_TILD
-    ..... --> PUNCT_TILD
-    ...... --> PUNCT_TILD
-    ....... --> PUNCT_TILD
-
-    , --> PUNCT_DOT
-    : --> PUNCT_DOT
-    ; --> PUNCT_DOT
+    ~  --> PUNCT_TILD
+    –  --> PUNCT_TILD
+    —  --> PUNCT_TILD
+    
     ! --> PUNCT_EXCLAM
     ? --> PUNCT_INTERR
-    · --> PUNCT_DOT
-
-    :: --> PUSTA_3
-
+   
     \** Apostrophe **\
 
     ' --> {NULL}
@@ -234,10 +261,6 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     « --> DQUOT_OPEN
     » --> DQUOT_CLOSE
 
-    - --> {NULL}
-    – --> PUNCT_TILD
-    — --> PUNCT_TILD
-
     [ --> PUNCT_PAREN_L
     ] --> PUNCT_PAREN_R
     ( --> PUNCT_PAREN_L
@@ -248,7 +271,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \**    > --> PUNCT_PAREN_R : cannot be used since it is already used as a letter in group litteral **\
 
     \** Not universal between fonts ... **\
-    $ --> BOOKMARK_SIGN
+    $ --> ELVISH_PAREN
     ≤ --> RING_MARK_L \** Ring inscription left beautiful stuff **\
     ≥ --> RING_MARK_R \** Ring inscription right beautiful stuff **\
 

data/glaemresources/modes/{rlyehian.glaem → rlyehian-tengwar.glaem}

@@ -35,12 +35,14 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 	\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"
+  \entry "0.1.2" "Added support for new unicode charsets"   
+  \entry "0.1.3" "Added support for the Tengwar Telcontar font"
 \end
 
 \language "R'lyehian"
 \writing  "Tengwar"
 \mode     "R'lyehian Tengwar - G*"
-\version  "0.1.1"
+\version  "0.1.3"
 \authors  "H.P.Lovecraft & The Great Ancient Gods, impl. Fthalagn"
 
 \world      other_world
@@ -53,7 +55,16 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \charset  tengwar_ds_eldamar  false
 \charset  tengwar_ds_annatar  false
 \charset  tengwar_ds_elfica   false
+
+\charset  tengwar_guni_sindarin false
+\charset  tengwar_guni_parmaite false
+\charset  tengwar_guni_eldamar  false
+\charset  tengwar_guni_annatar  false
+\charset  tengwar_guni_elfica   false
+
 \charset  tengwar_freemono    false
+\charset  tengwar_telcontar   false
+
 
 \beg      options
 \end
@@ -178,7 +189,7 @@ y palatal semi vowel ?
     {O_LOOP}        === O_TEHTA
     {U_LOOP}        === U_TEHTA
        
-    {TEHTAR}            === A_TEHTA      * E_TEHTA      * I_TEHTA    * O_TEHTA     * U_TEHTA * SEV_TEHTA
+    {TEHTAR}            === A_TEHTA      * E_TEHTA      * I_TEHTA    * O_TEHTA     * U_TEHTA * WA_TEHTA
   
     [{VOWELS}]          --> TELCO [{TEHTAR}]  \** Replace isolated short vowels **\
   
@@ -268,7 +279,7 @@ y palatal semi vowel ?
     > --> PUNCT_PAREN_R  
 
     \** Not universal between fonts ... **\
-    $ --> BOOKMARK_SIGN
+    $ --> ELVISH_PAREN
     ≤ --> RING_MARK_L \** Ring inscription left beautiful stuff **\
     ≥ --> RING_MARK_R \** Ring inscription right beautiful stuff **\
   \end

data/glaemresources/modes/{sindarin-daeron.glaem → sindarin-cirth-daeron.glaem}

@@ -28,12 +28,13 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \entry 0.0.2 "Added thorn as equivalent for th"
   \entry 0.0.3 "Moved out space to general element"
   \entry 0.0.4 "Fixed wrong ch, hw, h"
+  \entry 0.0.5 "Added disambiguations from the tengwar modes. Reworked median point behaviour, and ng."
 \end
 
 \language "Sindarin"
 \writing  "Cirth"
 \mode     "Sindarin Cirth - Angerthas Daeron"
-\version  "0.0.4"
+\version  "0.0.5"
 \authors  "J.R.R. Tolkien, impl. Talagan (Benjamin Babut)"
 
 \world      arda
@@ -44,10 +45,29 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \** We redefine the output space to have something beautiful, especially with erebor1 and erebor2 **\ 
 \outspace CIRTH_SPACE_BIG
 
+\beg options
+  \beg option hyphen HYPHEN_WORD_BREAKER
+    \value HYPHEN_WORD_BREAKER  0
+    \value HYPHEN_WORD_JOINER   1
+  \end
+\end
+
+
 \beg      preprocessor
   \** Work exclusively downcase **\
   \downcase
   
+  \if "hyphen == HYPHEN_WORD_JOINER"
+    \** Replace hyphen by median point **\
+    \substitute "-" "·"  
+  \else
+    \** Replace hyphen by glaemscribe's word breaker **\
+    \substitute "-" "|"
+  \endif
+  
+  \** Add keyboard friendly word joiner **\
+  \substitute "*" "·"
+  
   \** Simplify trema vowels **\
   \substitute ä a
   \substitute ë e
@@ -63,6 +83,25 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \rxsubstitute "(ō|ô|oo)" "ó"
   \rxsubstitute "(ū|û|uu)" "ú"
   \rxsubstitute "(ȳ|ŷ|yy)" "ý"
+  
+  \** Special case of starting 'i' before vowels, replace i by j **\     
+  \rxsubstitute "\\bi([aeouyáāâéēêíīîóōôúūûýȳŷ])" "j\\1"
+  
+  \** Special case of diphtong aw. Before vowels, do not treat 'aw' as diphthong, 
+  since it seems more logical that aw would behave as a semi vowel **\
+  \rxsubstitute "aw([aeouyáāâéēêíīîóōôúūûýȳŷ])" "a|w\\1"
+
+  \** Special case for ng : before the vast majority of consonnants, treat as ŋ **\
+  \** Don't include r / l / lh / w **\
+  \rxsubstitute "ng([tpckbdfðvnmhs])" "ŋ\\1"
+  
+  \** Avoid mutated ng of being treated as strong middle word n|g (ex : i·ngelaidh [iŋɛlaið] ) **\
+  \substitute "·ng" "·ŋ"  
+  \** But avoid losing the strong g in nasal mutation of g (ex : in·Gelydh [iŋgɛlyð]] ) **\
+  \substitute "n·g" "·ŋg"
+  \** Use median dot as word joiner **\
+  \substitute "·" ""
+  
 \end
 
 \beg      processor
@@ -115,16 +154,11 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     (k,c)     --> CIRTH_18
     (kh,ch)   --> CIRTH_20
     
-    ghw   --> CIRTH_26
-    gw    --> CIRTH_24
     
     h     --> CIRTH_54 \**  13 is more eng. ch like in chin and 15 is more eng. sh like in shoe **\
-    hw    --> CIRTH_5
     
     j     --> CIRTH_14
     
-    khw   --> CIRTH_25
-    kw    --> CIRTH_23
     l     --> CIRTH_31
     lh    --> CIRTH_32
     m     --> CIRTH_6
@@ -133,14 +167,11 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     n     --> CIRTH_12
     nc_   --> CIRTH_22 CIRTH_18 \** equals ŋc **\
     nd    --> CIRTH_38
-    ng    --> CIRTH_33
-  
-    _ng   --> CIRTH_22
-    ng_   --> CIRTH_22 
-    ŋ     --> CIRTH_22
+    
+    \** Normalisation of ng **\
+    (ng,ngg,ŋg,ñg)  --> CIRTH_33 \** strong **\
+    (ng_,_ng,ŋ,ñ)   --> CIRTH_22 \** weak **\
   
-    nw    --> CIRTH_28
-    ngw   --> CIRTH_27
     nj    --> CIRTH_17
     r     --> CIRTH_29
     rh    --> CIRTH_30
@@ -148,8 +179,18 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     sh    --> CIRTH_15
     ss    --> CIRTH_36
     (þ,th) --> CIRTH_10
-    w     --> CIRTH_44
     zh    --> CIRTH_16
+    
+    \** Labials **\
+    hw                --> CIRTH_5
+    ghw               --> CIRTH_26
+    gw                --> CIRTH_24    
+    (ng,ngg,ŋg,ñg)w   --> CIRTH_27     \** STRONG NG + W **\
+    khw               --> CIRTH_25
+    kw                --> CIRTH_23
+    nw                --> CIRTH_28
+    w                 --> CIRTH_44
+
   \end
   
   \beg    rules punctuation