glaemscribe 1.1.14 → 1.2.0

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

data/glaemresources/modes/{sindarin-beleriand.glaem → sindarin-tengwar-beleriand.glaem}

@@ -33,12 +33,16 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \entry "0.1.1" "Added support for inlined raw tengwar"
   \entry "0.1.2" "Fine tuning handling of the aw diphthong (Thanks to Dmitry Kourmyshov!)"
   \entry "0.1.3" "Merging au/aw"
+  \entry "0.1.4" "Added support for new unicode charsets"   
+  \entry "0.1.5" "Added support for the Tengwar Telcontar font"
+  \entry "0.1.6" "Corrected use of silme_nuquerna in ns / y, added a few exotic combinations. Reworked median point behaviour, and ng."
+  \entry "0.1.7" "Added variants with dot for short vowels, added gasdil."
 \end
 
 \language "Sindarin"
 \writing  "Tengwar"
 \mode     "Sindarin Tengwar - Beleriand"
-\version  "0.1.3"
+\version  "0.1.6"
 \authors  "J.R.R. Tolkien, impl. Talagan (Benjamin Babut)"
 
 \world      arda
@@ -51,10 +55,64 @@ 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
 
+  \beg option short_a SHORT_A_WITHOUT_DOT
+    \radio
+    \value SHORT_A_WITHOUT_DOT 0
+    \value SHORT_A_WITH_DOT    1
+  \end
+  
+  \beg option short_e SHORT_E_WITHOUT_DOT
+    \radio
+    \value SHORT_E_WITHOUT_DOT 0
+    \value SHORT_E_WITH_DOT    1
+  \end
+  
+  \beg option short_i SHORT_I_WITHOUT_DOT
+    \radio
+    \value SHORT_I_WITHOUT_DOT 0
+    \value SHORT_I_WITH_DOT    1
+  \end
+  
+  \beg option short_o SHORT_O_WITHOUT_DOT
+    \radio
+    \value SHORT_O_WITHOUT_DOT 0
+    \value SHORT_O_WITH_DOT    1
+  \end
+  
+  \beg option short_u SHORT_U_WITHOUT_DOT
+    \radio
+    \value SHORT_U_WITHOUT_DOT 0
+    \value SHORT_U_WITH_DOT    1
+  \end
+  
+  \beg option short_y SHORT_Y_WITHOUT_DOT
+    \radio
+    \value SHORT_Y_WITHOUT_DOT 0
+    \value SHORT_Y_WITH_DOT    1
+  \end  
+  
+  \beg option apostrophe APOSTROPHE_IGNORED
+    \value APOSTROPHE_IGNORED 0
+    \value APOSTROPHE_GASDIL  1
+  \end
+  
+  \beg option hyphen HYPHEN_WORD_BREAKER
+    \value HYPHEN_WORD_BREAKER  0
+    \value HYPHEN_WORD_JOINER   1
+  \end
+
   \beg option beleriand_aw_diphthong AW_VILYA_AT_ENDINGS_CURL_ELSE
     \value AW_VILYA_AT_ENDINGS_CURL_ELSE 0
     \value AW_ALWAYS_VILYA 1
@@ -79,6 +137,17 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   \** 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
@@ -105,6 +174,17 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
   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 "·" ""
+
   \** Preprocess numbers **\
   \elvish_numbers "\\eval numbers_base" "\\eval reverse_numbers"
 \end
@@ -143,34 +223,62 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     {OE}                === {O}{E}
              
     {K}                 === (c,k)
-
-    \** RULES **\
-    {A}                 --> OSSE
-    {E}                 --> YANTA
-    {I}                 --> TELCO
-    {O}                 --> ANNA
-    {U}                 --> URE
     
-    {Y}                 --> SILME_NUQUERNA_ALT
+    \if "short_a == SHORT_A_WITH_DOT"
+      {A}                 --> OSSE I_TEHTA
+    \else
+      {A}                 --> OSSE
+    \endif
+    
+    \if "short_e == SHORT_E_WITH_DOT"
+      {E}                 --> YANTA I_TEHTA
+    \else
+      {E}                 --> YANTA
+    \endif
+    
+    \if "short_i == SHORT_I_WITH_DOT"
+      {I}                 --> TELCO I_TEHTA
+    \else
+      {I}                 --> TELCO
+    \endif
+    
+    \if "short_o == SHORT_O_WITH_DOT"
+      {O}                 --> ANNA I_TEHTA
+    \else
+      {O}                 --> ANNA
+    \endif
+    
+    \if "short_u == SHORT_U_WITH_DOT"
+      {U}                 --> URE I_TEHTA
+    \else
+      {U}                 --> URE
+    \endif
+
+    \if "short_y == SHORT_Y_WITH_DOT"
+      {Y}                 --> SILME_NUQUERNA I_TEHTA
+    \else
+      {Y}                 --> SILME_NUQUERNA
+    \endif
 
     {AA}                --> OSSE  E_TEHTA
     {EE}                --> YANTA E_TEHTA
     {II}                --> TELCO E_TEHTA
     {OO}                --> ANNA  E_TEHTA
     {UU}                --> URE   E_TEHTA
-    {YY}                --> SILME_NUQUERNA_ALT E_TEHTA
+    {YY}                --> SILME_NUQUERNA E_TEHTA
 
-    {AE}                --> OSSE  YANTA  \** Should chose between OSSE YANTA and OSSE THSUP_TICK_INV_L. Old tengscribe had second one, amanye tenceli has first one. **\ 
+    \** Should chose between OSSE YANTA and OSSE THSUP_TICK_INV. Old tengscribe had second one, amanye tenceli has first one. **\ 
+    {AE}                --> OSSE  YANTA  
     {AI}                --> OSSE  Y_TEHTA
-    {AU}                --> OSSE  SEV_TEHTA 
+    {AU}                --> OSSE  WA_TEHTA 
     
     \if "beleriand_aw_diphthong == AW_VILYA_AT_ENDINGS_CURL_ELSE"
-      ({AU},{AW})         --> OSSE SEV_TEHTA
+      ({AU},{AW})         --> OSSE WA_TEHTA
       ({AU},{AW})_        --> OSSE VILYA
     \elsif "beleriand_aw_diphthong == AW_ALWAYS_VILYA"
       ({AU},{AW})         --> OSSE VILYA
     \elsif "beleriand_aw_diphthong == AW_ALWAYS_CURL"
-      ({AU},{AW})         --> OSSE SEV_TEHTA
+      ({AU},{AW})         --> OSSE WA_TEHTA
     \endif
       
     {EI}                --> YANTA Y_TEHTA
@@ -197,9 +305,13 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
     [{L2}] --> [{_L2_}]
 
-    mb   --> UMBAR  {NASAL}
-    nd   --> ANDO   {NASAL}
-
+    mb          --> UMBAR  {NASAL}
+    nd          --> ANDO   {NASAL}
+    
+    \** /ŋg/ : this is ng in middle of words + might be found at word start on mutation.
+    \** See also final/initial ng_ / _ng below **\
+    (ng,ngg,ŋg,ñg)    --> ANGA   {NASAL} 
+    
     \** ======== **\
     \** 3RD LINE **\
     \** ======== **\
@@ -224,7 +336,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     \** ======== **\
     \** 5TH LINE **\
     \** ======== **\
-    {L5}    === nn    * mm    * ng
+    {L5}    === nn    * mm    * (ng_,_ng,ŋ,ñ)
     {_L5_}  === NUMEN * MALTA * NOLDO 
 
     [{L5}] --> [{_L5_}]
@@ -253,7 +365,8 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
     [{S_LINE}] --> [{_S_LINE_}]
 
-    ns --> SILME_NUQUERNA {NASAL}
+    \** REMOVING NEXT ONE WHICH CLASHES WITH Y **\
+    \** ns --> SILME_NUQUERNA {NASAL} **\
 
     \** ======== **\
     \** OTHERS **\
@@ -266,12 +379,26 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     hw   --> HWESTA_SINDARINWA
 
     \** labialized consonants **\
-    dw   --> ANDO   SEV_TEHTA
-    gw   --> ANGA   SEV_TEHTA
-    lw   --> LAMBE  SEV_TEHTA
-    nw   --> ORE    SEV_TEHTA
-    rw   --> ROMEN  SEV_TEHTA 
-
+    bw              --> UMBAR  WA_TEHTA \** Gnomish **\
+    dw              --> ANDO   WA_TEHTA
+    gw              --> ANGA   WA_TEHTA
+    lw              --> LAMBE  WA_TEHTA
+    nw              --> ORE    WA_TEHTA
+    rw              --> ROMEN  WA_TEHTA 
+    (ng,ngg,ŋg,ñg)w --> ANGA {NASAL} WA_TEHTA
+    (_ng,ng_,ŋ,ñ)w  --> NOLDO  WA_TEHTA
+    
+    \if "apostrophe == APOSTROPHE_IGNORED"
+      ' --> {NULL}
+      ’ --> {NULL}
+    \else
+      \** use gasdil **\
+      ' --> HALLA
+      ’ --> HALLA
+    \endif
+    
+    \** Forced gasdil **\
+    ° --> HALLA
   \end
   
   \beg    rules punctuation
@@ -297,8 +424,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
     \** Apostrophe **\
 
-    ' --> {NULL}
-    ’ --> {NULL}
+
     
     \** NBSP **\
     {NBSP} --> NBSP
@@ -320,7 +446,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
     > --> 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