glaemscribe 1.0.0

data/glaemresources/charsets/unicode_gothic.cst

@@ -0,0 +1,64 @@
+\**
+
+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/>.
+
+**\
+
+\** Charset for the analecta font used by the gothic mode **\ 
+\** Very incomplete outside of the gothic range **\ 
+\** Minimal service here ... **\
+
+\**   **\ \char 20 SPACE  
+\** , **\ \char 2C COMA
+\** . **\ \char 2E PERIOD
+\** : **\ \char 3A COLON
+\** ; **\ \char 3B SEMICOLON
+
+\** Gothic part **\
+\** 𐌰 **\ \char 10330 AZA  
+\** 𐌱 **\ \char 10331 BERCNA  
+\** 𐌳 **\ \char 10333 DAAZ  
+\** 𐌴 **\ \char 10334 EYZ  
+\** 𐍆 **\ \char 10346 FE  
+\** 𐌲 **\ \char 10332 GEUUA  
+\** 𐌷 **\ \char 10337 HAAL  
+\** 𐌹 **\ \char 10339 IIZ  
+\** 𐌾 **\ \char 1033E GAAR  
+\** 𐌺 **\ \char 1033A CHOZMA  
+\** 𐌻 **\ \char 1033B LAAZ  
+\** 𐌼 **\ \char 1033C MANNA  
+\** 𐌽 **\ \char 1033D NOICZ  
+\** 𐍉 **\ \char 10349 UTAL 
+\** 𐍀 **\ \char 10340 PERTRA  
+\** 𐌵 **\ \char 10335 QUETRA  
+\** 𐍂 **\ \char 10342 REDA  
+\** 𐍃 **\ \char 10343 SUGIL  
+\** 𐍄 **\ \char 10344 TYZ  
+\** 𐌸 **\ \char 10338 THYTH  
+\** 𐌿 **\ \char 1033F URAZ  
+\** 𐍇 **\ \char 10347 ENGUZ  
+\** 𐍅 **\ \char 10345 UUINNE  
+\** 𐌶 **\ \char 10336 EZEC  
+\** 𐍈 **\ \char 10348 UUAER  
+\** 𐍋 **\ \char 1034B IIZ_TREMA \** Special Glaemscrafu ! **\ 
+\** 𐍁 **\ \char 10341 ? 
+\** 𐍊 **\ \char 1034A ? 
+

data/glaemresources/charsets/unicode_runes.cst

@@ -0,0 +1,120 @@
+\**
+
+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/>.
+
+**\
+
+\** Charset for the pfeffermediaeval font used by the furtharc mode **\ 
+\** Very incomplete outside of the runes range **\
+\** Minimal service here ... **\ 
+
+\**   **\ \char 20 SPACE                      
+\** , **\ \char 2C COMA
+\** . **\ \char 2E PERIOD 
+\** ; **\ \char 3B SEMICOLON   
+\** ᚠ **\ \char 16A0 FEHU FEOH FE 
+\** ᚡ **\ \char 16A1 RUNIC_V 
+\** ᚢ **\ \char 16A2 URUZ UR 
+\** ᚣ **\ \char 16A3 YR 
+\** ᚤ **\ \char 16A4 RUNIC_Y 
+\** ᚥ **\ \char 16A5 RUNIC_W 
+\** ᚦ **\ \char 16A6 THURISAZ THURS THORN 
+\** ᚧ **\ \char 16A7 ETH 
+\** ᚨ **\ \char 16A8 ANSUZ 
+\** ᚩ **\ \char 16A9 OS 
+\** ᚪ **\ \char 16AA AC 
+\** ᚫ **\ \char 16AB AESC 
+\** ᚬ **\ \char 16AC LONG_BRANCH_OSS 
+\** ᚭ **\ \char 16AD SHORT_TWIG_OSS 
+\** ᚮ **\ \char 16AE RUNIC_O 
+\** ᚯ **\ \char 16AF RUNIC_OE 
+\** ᚰ **\ \char 16B0 RUNIC_ON 
+\** ᚱ **\ \char 16B1 RAIDO RAD REID 
+\** ᚲ **\ \char 16B2 KAUNA 
+\** ᚳ **\ \char 16B3 CEN 
+\** ᚴ **\ \char 16B4 KAUN 
+\** ᚵ **\ \char 16B5 RUNIC_G 
+\** ᚶ **\ \char 16B6 ENG 
+\** ᚷ **\ \char 16B7 GEBO GYFU 
+\** ᚷ **\ \char 16B8 GAR 
+\** ᚹ **\ \char 16B9 WUNJO WYNN 
+\** ᚺ **\ \char 16BA HAGLAZ 
+\** ᚻ **\ \char 16BB HAEGL 
+\** ᚼ **\ \char 16BC LONG_BRANCH_HAGALL 
+\** ᚽ **\ \char 16BD SHORT_TWIG_HAGALL 
+\** ᚾ **\ \char 16BE NAUDIZ NYD NAUD 
+\** ᚿ **\ \char 16BF SHORT_TWIG_NAUD 
+\** ᛀ **\ \char 16C0 DOTTED_N 
+\** ᛁ **\ \char 16C1 ISAZ IS ISS 
+\** ᛂ **\ \char 16C2 RUNIC_E 
+\** ᛃ **\ \char 16C3 JERAN 
+\** ᛄ **\ \char 16C4 GER 
+\** ᛅ **\ \char 16C5 LONG_BRANCH_AR 
+\** ᛆ **\ \char 16C6 SHORT_TWIG_AR 
+\** ᛇ **\ \char 16C7 IWAZ EOH 
+\** ᛈ **\ \char 16C8 PERTHO PEORTH 
+\** ᛉ **\ \char 16C9 ALGIZ EOLHX 
+\** ᛊ **\ \char 16CA SOWILO 
+\** ᛋ **\ \char 16CB SIGEL LONG_BRANCH_SOL 
+\** ᛌ **\ \char 16CC SHORT_TWIG_SOL 
+\** ᛍ **\ \char 16CD RUNIC_C 
+\** ᛎ **\ \char 16CE RUNIC_Z 
+\** ᛏ **\ \char 16CF TIWAZ TIR TYR 
+\** ᛐ **\ \char 16D0 SHORT_TWIG_TYR 
+\** ᛑ **\ \char 16D1 RUNIC_D 
+\** ᛒ **\ \char 16D2 BERKANAN BEORC BJARKAN 
+\** ᛔ **\ \char 16D4 DOTTED_P 
+\** ᛕ **\ \char 16D5 OPEN_P 
+\** ᛖ **\ \char 16D6 EHWAZ EH 
+\** ᛗ **\ \char 16D7 MANNAZ MAN 
+\** ᛘ **\ \char 16D8 LONG_BRANCH_MADR 
+\** ᛙ **\ \char 16D9 SHORT_TWIG_MADR 
+\** ᛚ **\ \char 16DA LAUKAZ LAGU LOGR 
+\** ᛛ **\ \char 16DB DOTTED_L 
+\** ᛜ **\ \char 16DC INGWAZ 
+\** ᛝ **\ \char 16DD ING 
+\** ᛞ **\ \char 16DE DAGAZ DAEG 
+\** ᛟ **\ \char 16DF OTHALAN ETHEL 
+\** ᛠ **\ \char 16E0 EAR 
+\** ᛡ **\ \char 16E1 IOR 
+\** ᛢ **\ \char 16E2 CWEORTH 
+\** ᛣ **\ \char 16E3 CALC 
+\** ᛤ **\ \char 16E4 CEALC 
+\** ᛥ **\ \char 16E4 STAN 
+\** ᛦ **\ \char 16E6 LONG_BRANCH_YR 
+\** ᛧ **\ \char 16E7 SHORT_TWIG_YR 
+\** ᛨ **\ \char 16E8 ICELANDIC_YR 
+\** ᛩ **\ \char 16E9 RUNIC_Q 
+\** ᛪ **\ \char 16EA RUNIC_X 
+\** ᛫ **\ \char 16EB RUNIC_SINGLE_PUNCTUATION 
+\** ᛬ **\ \char 16EC RUNIC_MULTIPLE_PUNCTUATION 
+\** ᛭ **\ \char 16ED RUNIC_CROSS_PUNCTUATION
+\** ᛮ **\ \char 16EE RUNIC_ARLAUG_SYMBOL 
+\** ᛯ **\ \char 16EF RUNIC_TVIMADUR_SYMBOL 
+\** ᛰ **\ \char 16F0 RUNIC_BELGTHOR_SYMBOL 
+\** ᛱ **\ \char 16F1 RUNIC_LETTER_K 
+\** ᛲ **\ \char 16F2 RUNIC_LETTER_SH 
+\** ᛳ **\ \char 16F3 RUNIC_LETTER_OO   
+\** ᛴ **\ \char 16F4 RUNIC_LETTER_FRANKS_CASKET_OS 
+\** ᛵ **\ \char 16F5 RUNIC_LETTER_FRANKS_CASKET_IS 
+\** ᛶ **\ \char 16F6 RUNIC_LETTER_FRANKS_CASKET_EH 
+\** ᛷ **\ \char 16F7 RUNIC_LETTER_FRANKS_CASKET_AC 
+\** ᛸ **\ \char 16F8 RUNIC_LETTER_FRANKS_CASKET_AESC

data/glaemresources/modes/adunaic.glaem

@@ -0,0 +1,251 @@
+\**
+
+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/>.
+
+**\
+
+\**  Adunaic mode for glaemscribe (MAY BE INCOMPLETE) **\
+\language Adûnaic
+\writing  Tengwar
+\mode     Glaemscrafu
+\version  0.0.1
+\authors  "Talagan (Benjamin Babut)"
+
+\charset  tengwar_ds true
+
+\beg      options
+  \option reverse_numbers true
+  \beg option numbers_base BASE_12
+    \value    BASE_10 10
+    \value    BASE_12 12
+  \end
+\end
+
+\beg      preprocessor
+  \** Work exclusively downcase **\
+  \downcase
+  
+  \** Simplify trema vowels **\
+  \substitute "ä" "a"
+  \substitute "ë" "e"
+  \substitute "ï" "i"
+  \substitute "ö" "o"
+  \substitute "ü" "u"
+  \substitute "ÿ" "y"
+  
+  \** Dis-ambiguate long vowels **\
+  \rxsubstitute "(ā|â|aa)" "á"
+  \rxsubstitute "(ē|ê|ee)" "é"
+  \rxsubstitute "(ī|î|ii)" "í"
+  \rxsubstitute "(ō|ô|oo)" "ó"
+  \rxsubstitute "(ū|û|uu)" "ú"
+  \rxsubstitute "(ȳ|ŷ|yy)" "ý"
+  
+  \** Preprocess numbers **\
+  \elvish_numbers "\\eval numbers_base" "\\eval reverse_numbers"
+\end
+
+\beg      processor
+
+  \beg    rules litteral  
+    {A}   === a
+    {AA}  === á
+    {E}   === e
+    {EE}  === é
+    {I}   === i
+    {II}  === í
+    {O}   === o
+    {OO}  === ó
+    {U}   === u
+    {UU}  === ú
+
+    \** Short diphthongs **\
+    {AI}  === {A}{I}
+    {AU}  === {A}{U}
+
+    \** LONG diphthongs **\      
+    {AAI} === {AA}{I} \** âi **\
+    {AAU} === {AA}{U} \** âu **\
+    {EEI} === {EE}{I} \** êi **\
+    {EEU} === {EE}{U} \** êu **\
+    {OOI} === {OO}{I} \** ôi **\
+    {OOU} === {OO}{U} \** ôu **\
+
+    {SDIPHTHONGS}  === {AI}            * {AU}
+    {SDIPHTHENGS}  === YANTA A_TEHTA_L  * URE A_TEHTA_L 
+                   
+    {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_TEHTA_XS YANTA  * ARA O_TEHTA_XS URE
+                   
+    {VOWELS}      === {A}         * {E}         * {I}           * {O}           * {U}    
+    {TEHTA_XS}    === A_TEHTA_XS  * E_TEHTA_XS  * I_TEHTA_XS    * O_TEHTA_XS    * U_TEHTA_XS 
+    {TEHTA__S}    === A_TEHTA_S   * E_TEHTA_S   * I_TEHTA_S     * O_TEHTA_S     * U_TEHTA_S 
+    {TEHTA__L}    === A_TEHTA_L   * E_TEHTA_L   * I_TEHTA_L     * O_TEHTA_L     * U_TEHTA_L 
+    {TEHTA_XL}    === A_TEHTA_XL  * E_TEHTA_XL  * I_TEHTA_XL    * O_TEHTA_XL    * U_TEHTA_XL 
+                   
+    {LVOWELS}     === {AA}            * {EE}            * {II}            * {OO}            * {UU}
+    {LVOWTNG}     === ARA A_TEHTA_XS  * ARA E_TEHTA_XS  * ARA I_TEHTA_XS  * ARA O_TEHTA_XS  * ARA U_TEHTA_XS 
+
+    \** 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 **\
+    [{SDIPHTHONGS}]  --> [{SDIPHTHENGS}]  \** Replace short diphthongs **\
+    [{LDIPHTHONGS}]  --> [{LDIPHTHENGS}]  \** Replace long diphthongs **\
+
+    \** ================ **\
+    \**    CONSONANTS    **\
+    \** ================ **\     
+    {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}]       -->  [ {L1_T} ]
+    [{L1_S}]{V_D}  -->  [ {L1_T} ]{T_S_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}]       --> [{L2_T}] 
+    [{L2_S}]{V_D}  --> [{L2_T}]{T_XL_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_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_1_S}]        --> [{L3_1_T}] 
+    [{L3_1_S}]{V_D}   --> [{L3_1_T}]{T_S_D} 
+    [{L3_2_S}]        --> [{L3_2_T}] 
+    [{L3_2_S}]{V_D}   --> [{L3_2_T}]{T_L_D} 
+
+    {L4_S}            === nd    * mb    * ng
+    {L4_T}            === ANTO  * AMPA  * UNQUE
+    [{L4_S}]          --> [{L4_T}] 
+    [{L4_S}]{V_D}     --> [{L4_T}]{T_XL_D} 
+
+    {L5_S}            === n     * m     * nn                * mm
+    {L5_T}            === NUMEN * MALTA * NUMEN DASH_INF_L  * MALTA DASH_INF_L
+    [{L5_S}]          --> [{L5_T}] 
+    [{L5_S}]{V_D}     --> [{L5_T}]{T_XL_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
+    [r * {L6_S}]      --> [ ORE   * {L6_T}] 
+    [r * {L6_S}]{V_D} --> [ ROMEN * {L6_T}]{T_S_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                 --> SILME                   \** Any other pos, up **\
+    z{V_D}            --> ESSE_NUQUERNA {T_S_D}   \** Before a vowel goes down **\
+    z                 --> ESSE                    \** Any other pos, up **\
+
+    h{V_D}            --> HYARMEN {T_XS_D}
+    h                 --> HYARMEN
+    hh{V_D}           --> HYARMEN DASH_INF_L {T_XS_D}
+    hh                --> HYARMEN DASH_INF_L
+                      
+    l{V_D}            --> LAMBE {T_XL_D}
+    l                 --> LAMBE
+                      
+    ll{V_D}           --> LAMBE LAMBE_MARK_TILD {T_XL_D}
+    ll                --> LAMBE LAMBE_MARK_TILD
+  
+  \end
+  
+  \beg rules punctutation
+    . --> 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 
+    
+    - --> PUNCT_DOT    
+    – --> WAVE_MED_SIMPLE  
+    — --> WAVE_MED_DOUBLE
+ 
+    [ --> PUNCT_PAREN_L
+    ] --> PUNCT_PAREN_R
+    ( --> PUNCT_PAREN_L
+    ) --> PUNCT_PAREN_R
+    { --> PUNCT_PAREN_L
+    } --> PUNCT_PAREN_R
+    < --> PUNCT_PAREN_L
+    > --> PUNCT_PAREN_R  
+
+    \** Not universal between fonts ... **\
+    $ --> BOOKMARK_SIGN
+    ≤ --> RING_MARK_L \** Ring inscription left beautiful stuff **\
+    ≥ --> RING_MARK_R \** Ring inscription right beautiful stuff **\
+  \end
+
+  \beg rules numbers
+    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
+    A --> NUM_10
+    B --> NUM_11   
+  \end
+  
+\end
+

data/glaemresources/modes/blackspeech-annatar.glaem

@@ -0,0 +1,318 @@
+\**
+
+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/>.
+
+**\
+
+\** BlackSpeech ring mode for glaemscribe (FAR FROM BEING COMPLETE!!!) **\
+
+\language "Black Speech"
+\writing  "Tengwar"
+\mode     "Ring Style / Cursive"
+\version  "0.0.1"
+\authors  "Talagan (Benjamin Babut)"
+
+\charset  tengwar_ds true
+
+\beg      options
+  \option reverse_numbers true
+  \beg option numbers_base BASE_12
+    \value    BASE_10 10
+    \value    BASE_12 12
+  \end
+\end
+
+\beg      preprocessor
+  \** Work exclusively downcase **\
+  \downcase
+  
+  \** Simplify trema vowels **\
+  \substitute ä a
+  \substitute ë e
+  \substitute ï i
+  \substitute ö o
+  \substitute ü u
+  \substitute ÿ y
+  
+  \** Dis-ambiguate long vowels **\
+  \rxsubstitute "(ā|â|aa)" "á"
+  \rxsubstitute "(ē|ê|ee)" "é"
+  \rxsubstitute "(ī|î|ii)" "í"
+  \rxsubstitute "(ō|ô|oo)" "ó"
+  \rxsubstitute "(ū|û|uu)" "ú"
+  
+  \** Preprocess numbers **\
+  \elvish_numbers "\\eval numbers_base" "\\eval reverse_numbers"
+\end
+  
+\beg processor
+
+  \beg rules litteral
+    {A}                 === a
+    {AA}                === á
+    {E}                 === e
+    {EE}                === é
+    {I}                 === i
+    {II}                === í
+    {O}                 === o
+    {OO}                === ó
+    {U}                 === u
+    {UU}                === ú
+    
+    {AI}                === {A}{I} \** attested **\
+    {AU}                === {A}{U} \** attested **\
+    {OI}                === {O}{I} \** Not quite sure (dushgoi) **\
+    
+    {K}                 === (c,k)
+    
+    \** VOWELS **\
+    {VOWELS}            === {A}               * {E}               * {I}        * {O}                * {U}
+    {LVOWELS}           === {AA}              * {EE}              * {II}       * {OO}               * {UU}  
+    \** Reverse o and u **\
+    {TEHTA_XS}          === A_TEHTA_XS        * E_TEHTA_XS        * I_TEHTA_XS *  U_TEHTA_XS        * O_TEHTA_XS      
+    {TEHTA__S}          === A_TEHTA_S         * E_TEHTA_S         * I_TEHTA_S  *  U_TEHTA_S         * O_TEHTA_S     
+    {TEHTA__L}          === A_TEHTA_L         * E_TEHTA_L         * I_TEHTA_L  *  U_TEHTA_L         * O_TEHTA_L     
+    {TEHTA_XL}          === A_TEHTA_XL        * E_TEHTA_XL        * I_TEHTA_XL *  U_TEHTA_XL        * O_TEHTA_XL          
+    \** Double tehtas **\ 
+    {DTEHTA_XS}         === A_TEHTA_DOUBLE_XS * E_TEHTA_DOUBLE_XS * Y_TEHTA_XS * U_TEHTA_DOUBLE_XS  * O_TEHTA_DOUBLE_XS 
+    {DTEHTA_S}          === A_TEHTA_DOUBLE_S  * E_TEHTA_DOUBLE_S  * Y_TEHTA_S  * U_TEHTA_DOUBLE_S   * O_TEHTA_DOUBLE_S  
+    {DTEHTA_L}          === A_TEHTA_DOUBLE_L  * E_TEHTA_DOUBLE_L  * Y_TEHTA_L  * U_TEHTA_DOUBLE_L   * O_TEHTA_DOUBLE_L   
+    {DTEHTA_XL}         === A_TEHTA_DOUBLE_XL * E_TEHTA_DOUBLE_XL * Y_TEHTA_XL * U_TEHTA_DOUBLE_XL  * O_TEHTA_DOUBLE_XL
+        
+    {DIPHTHONGS}         === {AI}              * {AU}              *  {OI}              
+    {DIPHTHENGS}         === YANTA A_TEHTA_L    * URE A_TEHTA_L     * YANTA U_TEHTA_L   
+     
+    {V_D_KER}           === [ {VOWELS}   * {LVOWELS}    * {DIPHTHONGS} ]
+    {V_D_IMG_XS}        === [ {TEHTA_XS} * {DTEHTA_XS}  * {DIPHTHENGS} ]
+    {V_D_IMG__S}        === [ {TEHTA__S} * {DTEHTA_L}   * {DIPHTHENGS} ]
+    {V_D_IMG__L}        === [ {TEHTA__L} * {DTEHTA_S}   * {DIPHTHENGS} ]
+    {V_D_IMG_XL}        === [ {TEHTA_XL} * {DTEHTA_XL}  * {DIPHTHENGS} ]
+    
+    [{VOWELS}]          -->   TELCO [{TEHTA_XS}]  \** Replace isolated short vowels **\
+    [{LVOWELS}]         -->   ARA   [{TEHTA_XS}]  \**  Replace long vowels **\
+    [{DIPHTHONGS}]       -->  [{DIPHTHENGS}]  \**  Replace diphthongs **\
+    
+    \** CONSONANT RULES (could be factorized with crossrules) **\
+    
+    \** ======================== **\
+         
+    l               --> LAMBE
+    \** If we look closely on the ring inscription, **\
+    \** we can see the offset for the tehta starting point **\
+    \** That's why we use the XL tehtas **\
+    {V_D_KER}  l    --> LAMBE {V_D_IMG_XL}       
+    \** when telco follows, ligature with telco **\
+    l {V_D_KER}  _  --> LAMBE_LIG TELCO {V_D_IMG_XS}
+    
+    \** ======================== **\
+    
+    b                           --> UMBAR
+    {V_D_KER}   b              --> UMBAR {V_D_IMG_XL}
+    \** Attached l to b **\
+    l {V_D_KER}  b             --> LAMBE_LIG UMBAR {V_D_IMG_XL}
+    {V_D_KER}  l {V_D_KER}  b --> LAMBE_LIG {V_D_IMG_XL} UMBAR {V_D_IMG_XL}
+                                                    
+    d                           --> ANDO
+    {V_D_KER}   d              --> ANDO {V_D_IMG_XL}
+    \** Attached l to d **\
+    l {V_D_KER}  d             --> LAMBE_LIG ANDO {V_D_IMG_XL}
+    {V_D_KER}  l {V_D_KER}  d --> LAMBE_LIG {V_D_IMG_XL} ANDO {V_D_IMG_XL}
+                                          
+    f                           --> FORMEN 
+    {V_D_KER}   f              --> FORMEN_EXT {V_D_IMG__S} \** Beware. **\ 
+    \** Attached l to f **\
+    l {V_D_KER}  f             --> LAMBE_LIG FORMEN_EXT {V_D_IMG__S}
+    {V_D_KER}  l {V_D_KER}  f --> LAMBE_LIG {V_D_IMG_XL} FORMEN_EXT {V_D_IMG__S}
+                                           
+    g                           --> UNGWE
+    {V_D_KER}   g              --> UNGWE {V_D_IMG_XL}
+    \** Attached l to g **\
+    l {V_D_KER}  g             --> LAMBE_LIG UNGWE {V_D_IMG_XL}
+    {V_D_KER}  l {V_D_KER}  g --> LAMBE_LIG {V_D_IMG_XL} UNGWE {V_D_IMG_XL}
+     
+    gh                           --> UNGWE_EXT
+    {V_D_KER}   gh              --> UNGWE_EXT {V_D_IMG_XL}
+    \** Attached l to g **\
+    l {V_D_KER}  gh             --> LAMBE_LIG UNGWE_EXT {V_D_IMG_XL}
+    {V_D_KER}  l {V_D_KER}  gh --> LAMBE_LIG {V_D_IMG_XL} UNGWE_EXT {V_D_IMG_XL}
+    
+    h                           --> HYARMEN
+    {V_D_KER}   h              --> HYARMEN {V_D_IMG_XS}
+    \** Attached l to g **\
+    l {V_D_KER}  h             --> LAMBE_LIG HYARMEN {V_D_IMG_XS}
+    {V_D_KER}  l {V_D_KER}  h --> LAMBE_LIG {V_D_IMG_XL} HYARMEN {V_D_IMG_XS}
+          
+    {K}                          --> QUESSE
+    {V_D_KER}   {K}              --> QUESSE {V_D_IMG__L}
+    \** Attached l to g **\
+    l {V_D_KER}  {K}             --> LAMBE_LIG QUESSE {V_D_IMG__L}
+    {V_D_KER}  l {V_D_KER}  {K}  --> LAMBE_LIG {V_D_IMG_XL} QUESSE {V_D_IMG__L}
+          
+    {K}h                           --> HWESTA
+    {V_D_KER}   {K}h              --> HWESTA_EXT {V_D_IMG__L}
+    \** Attached l to g **\
+    l {V_D_KER}  {K}h             --> LAMBE_LIG HWESTA_EXT {V_D_IMG__L}
+    {V_D_KER}  l {V_D_KER}  {K}h --> LAMBE_LIG {V_D_IMG_XL} HWESTA_EXT {V_D_IMG__L}
+          
+    
+    m                               --> MALTA
+    {V_D_KER}  m                   --> MALTA {V_D_IMG_XL}
+    
+    mb                              --> UMBAR TILD_SUP_L
+    {V_D_KER}  mb                  --> UMBAR TILD_SUP_L {V_D_IMG_XL}
+    
+    mp                             --> PARMA TILD_SUP_S
+    {V_D_KER}  mp                  --> PARMA TILD_SUP_S {V_D_IMG__L}
+    
+    n                              --> NUMEN
+    {V_D_KER} n                    --> NUMEN {V_D_IMG_XL} 
+    
+    n{K}                           --> QUESSE TILD_SUP_S
+    {V_D_KER} n{K}                 --> QUESSE TILD_SUP_S {V_D_IMG__S} 
+    
+    p                               --> PARMA
+    
+    r                               --> ROMEN
+    {V_D_KER}  r                   --> ORE {V_D_IMG__L}
+    \** Attached l to r **\        
+    l {V_D_KER}  r                 --> LAMBE_LIG ORE {V_D_IMG__L}
+    {V_D_KER}  l {V_D_KER}  r     --> LAMBE_LIG {V_D_IMG_XL} ORE {V_D_IMG__L}
+    
+    
+    r                               --> ROMEN
+    r_                              --> ORE
+    {V_D_KER} r                    --> ORE {V_D_IMG__S}                                      
+    {V_D_KER} rb                   --> ORE {V_D_IMG__L} UMBAR                                  
+    {V_D_KER} rz                   --> ORE {V_D_IMG__L} ESSE
+    
+    s                               --> SILME
+    
+    
+    \** Beware sh is not the same if not preceeded by vowel **\
+    sh                              --> AHA
+    {A}sh                           --> AHA_EXT A_TEHTA_L           
+    {E}sh                           --> AHA_EXT E_TEHTA_L
+    {I}sh                           --> AHA_EXT I_TEHTA_L
+    {O}sh                           --> AHA_EXT U_TEHTA_S 
+    {U}sh                           --> AHA_EXT O_TEHTA_XS \** The best one still not satisfying... **\
+    {AA}sh                          --> ESSE_NUQUERNA A_TEHTA_DOUBLE_L 
+    {EE}sh                          --> ESSE_NUQUERNA E_TEHTA_DOUBLE_L
+    {II}sh                          --> ESSE_NUQUERNA Y_TEHTA_L
+    {OO}sh                          --> ESSE_NUQUERNA U_TEHTA_DOUBLE_S 
+    {UU}sh                          --> ESSE_NUQUERNA O_TEHTA_DOUBLE_XS
+    
+    t                               --> TINCO
+    {V_D_KER} t                    --> TINCO {V_D_IMG__L}
+    
+    th                              --> SULE
+    y                               --> ANNA
+    
+    z                               --> ESSE
+    
+    \** Need to break thisone too **\
+    {A}z                            --> ESSE_NUQUERNA A_TEHTA_L 
+    {E}z                            --> ESSE_NUQUERNA E_TEHTA_L
+    {I}z                            --> ESSE_NUQUERNA I_TEHTA_L
+    {O}z                            --> ESSE_NUQUERNA U_TEHTA_S 
+    {U}z                            --> ESSE_NUQUERNA O_TEHTA_S
+    {AA}z                           --> ESSE_NUQUERNA A_TEHTA_DOUBLE_L 
+    {EE}z                           --> ESSE_NUQUERNA E_TEHTA_DOUBLE_L
+    {II}z                           --> ESSE_NUQUERNA Y_TEHTA_L
+    {OO}z                           --> ESSE_NUQUERNA U_TEHTA_DOUBLE_S 
+    {UU}z                           --> ESSE_NUQUERNA O_TEHTA_DOUBLE_S
+  \end
+    
+  \beg rules punctuation
+    . --> 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
+    > --> PUNCT_PAREN_R
+
+    \** Not universal between fonts ... **\
+    $ --> BOOKMARK_SIGN
+    ≤ --> RING_MARK_L \** Ring inscription left beautiful stuff **\
+    ≥ --> RING_MARK_R \** Ring inscription right beautiful stuff **\
+
+  \end
+
+  \beg rules numbers
+    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
+    A --> NUM_10
+    B --> NUM_11      
+  \end
+
+\end
+
+
+
+
+
+
+
+
+
+ 
+