Mappings for representing English in Cirth (as in LOTR) and Futhorc/Runes (as in the Hobbit)

glaemresources/charsets/unicode_runes.cst

@@ -54,7 +54,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 \** ᚵ **\ \char 16B5 RUNIC_G 
 \** ᚶ **\ \char 16B6 ENG 
 \** ᚷ **\ \char 16B7 GEBO GYFU 
-\** ᚷ **\ \char 16B8 GAR 
+\** ᚸ **\ \char 16B8 GAR
 \** ᚹ **\ \char 16B9 WUNJO WYNN 
 \** ᚺ **\ \char 16BA HAGLAZ 
 \** ᚻ **\ \char 16BB HAEGL 

glaemresources/modes/english-cirth-erebor.glaem

@@ -0,0 +1,222 @@
+\**
+
+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", "Adapted to an English instead of Khuzdul mode from khuzdul-cirth-moria.glaem"
+\end
+
+\beg options
+  \option dots_for_spaces false
+\end
+
+\** This is the version of the Cirth used in the Title page of the Lord of the Rings **\
+\** See https://ring-lord.tripod.com/cirth/angerthaserebor.htm for a good reference **\
+\language "English"
+\writing  "Cirth"
+\mode     "English Cirth - Angerthas Erebor"
+\version  "0.0.1"
+\authors  "J.R.R. Tolkien, impl. David Fraser based on work of Talagan (Benjamin Babut)"
+
+\world      primary_related_to_arda
+\invention  jrrt
+
+\charset  cirth_ds true
+
+\if dots_for_spaces
+  \outspace CIRTH_PUNCT_MID_DOT
+\else
+  \** We redefine the output space to have something beautiful, especially with erebor1 and erebor2 **\ 
+  \outspace CIRTH_SPACE_BIG
+\endif
+
+\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)" "â"
+  \rxsubstitute "(ē|ê|ee)" "ê"
+  \rxsubstitute "(ī|î|ii)" "î"
+  \rxsubstitute "(ō|ô|oo)" "ô"
+  \rxsubstitute "(ū|û|uu)" "û"
+  \rxsubstitute "(ȳ|ŷ|yy)" "ŷ"
+\end
+
+\beg      processor
+
+  \beg    rules litteral
+
+
+    \** Note that several of these sequences are not expected to be used in English e.g. ghw **\
+    p   --> CIRTH_1
+    b   --> CIRTH_2
+    f   --> CIRTH_3
+    v   --> CIRTH_4
+    hw  --> CIRTH_5
+    m   --> CIRTH_6
+    mb  --> CIRTH_7
+    t   --> CIRTH_8
+    d   --> CIRTH_9
+    th  --> CIRTH_10
+    dh  --> CIRTH_11
+    r   --> CIRTH_12
+    ch  --> CIRTH_13
+    j   --> CIRTH_14
+    sh  --> CIRTH_15
+    zh  --> CIRTH_16
+    ks  --> CIRTH_17
+    k   --> CIRTH_18
+    g   --> CIRTH_19
+    kh  --> CIRTH_20
+    gh  --> CIRTH_21
+    n   --> CIRTH_22
+    kw  --> CIRTH_23
+    gw  --> CIRTH_24
+    khw --> CIRTH_25
+    ghw --> CIRTH_26
+    ngw --> CIRTH_27
+    nw  --> CIRTH_28
+    l   --> CIRTH_31
+    nd  --> CIRTH_33
+    s   --> CIRTH_35
+    ŋ   --> CIRTH_36  \** This is a pure velar nasal ŋ **\
+    ng  --> CIRTH_37  \** This represents ŋ followed by g which is common in English too **\
+    ou  --> CIRTH_38
+    ow  --> CIRTH_38
+    i   --> CIRTH_39
+    î   --> CIRTH_39 CIRTH_39
+    y   --> CIRTH_40
+    hy  --> CIRTH_41
+    (u,û) --> CIRTH_42
+    z   --> CIRTH_43
+    w   --> CIRTH_44
+    ü   --> CIRTH_45
+    e   --> CIRTH_46
+    ê   --> CIRTH_47
+    a   --> CIRTH_48
+    â   --> CIRTH_49
+    o   --> CIRTH_50
+    ô   --> CIRTH_51
+    ö   --> CIRTH_52
+    h   --> CIRTH_54
+    ə   --> CIRTH_55 \** This is a silent-e or schwa ə sound which occurs in English unstressed syllables **\
+    ʌ   --> CIRTH_56 \** This is the equivalent of a schwa for a stressed syllabel **\
+    ps  --> CIRTH_57
+    ts  --> CIRTH_58
+    +h  --> CIRTH_59
+    _&_ --> CIRTH_60
+    \** These are additional letters used as variations which don't have representation in the standard character set **\
+    eu  --> CIRTH_38
+    ew  --> CIRTH_38
+    ai  --> CIRTH_EREB_4
+    ay  --> CIRTH_EREB_4
+    au  --> CIRTH_EREB_5
+    aw  --> CIRTH_EREB_5
+    ea  --> CIRTH_EREB_6
+    oa  --> CIRTH_EREB_7
+    \** Not yet implemented:
+    over circumflex doubles the length of the consonant sound
+    single under-bar doubles the length of the vowel sound
+    single under-dot used to indicate a symbol that is a number
+    **\
+    \** These are alternative characters which can be selected by prefixing them with a + **\
+    +g   --> CIRTH_29
+    +gh  --> CIRTH_30
+    \** +h   --> CIRTH_34 **\
+    +ou  --> CIRTH_38_ALT
+    +ow  --> CIRTH_38_ALT
+    +ô   --> CIRTH_51_ALT
+    +ö   --> CIRTH_52_ALT
+    +n   --> CIRTH_53
+    +ə   --> CIRTH_55_ALT
+    +ʌ   --> CIRTH_56_ALT
+    \** Rules for particular common words **\
+    _the_ --> CIRTH_11 CIRTH_55
+    _of_  --> CIRTH_50 CIRTH_4
+  \end
+
+  \beg    rules punctuation
+    . --> CIRTH_PUNCT_THREE_DOTS
+    .. --> CIRTH_PUNCT_THREE_DOTS
+    ... --> CIRTH_PUNCT_THREE_DOTS
+    …   --> CIRTH_PUNCT_THREE_DOTS
+    .... --> CIRTH_PUNCT_THREE_DOTS
+    ..... --> CIRTH_PUNCT_THREE_DOTS
+    ...... --> CIRTH_PUNCT_THREE_DOTS
+    ....... --> CIRTH_PUNCT_THREE_DOTS
+
+    , --> CIRTH_PUNCT_MID_DOT
+    : --> CIRTH_PUNCT_TWO_DOTS
+    ; --> CIRTH_PUNCT_TWO_DOTS
+    ! --> CIRTH_PUNCT_THREE_DOTS
+    ? --> CIRTH_PUNCT_THREE_DOTS
+    · --> CIRTH_PUNCT_MID_DOT
+
+    - --> CIRTH_PUNCT_MID_DOT
+    – --> CIRTH_PUNCT_TWO_DOTS  
+    — --> CIRTH_PUNCT_TWO_DOTS
+
+    \** Apostrophe **\
+
+    ' --> {NULL}
+    ’ --> {NULL}
+
+    \** Quotes **\
+
+    “ --> {NULL}
+    ” --> {NULL}
+    « --> {NULL} 
+    » --> {NULL} 
+
+    [ --> CIRTH_PUNCT_THREE_DOTS_L
+    ] --> CIRTH_PUNCT_THREE_DOTS_L
+    ( --> CIRTH_PUNCT_THREE_DOTS_L
+    ) --> CIRTH_PUNCT_THREE_DOTS_L
+    { --> CIRTH_PUNCT_THREE_DOTS_L
+    } --> CIRTH_PUNCT_THREE_DOTS_L
+    < --> CIRTH_PUNCT_THREE_DOTS_L
+    > --> CIRTH_PUNCT_THREE_DOTS_L
+
+    / --> CIRTH_PUNCT_FOUR_DOTS
+  \end
+
+  \beg    rules numeric
+    \** Not yet implemented: single under-dot used to indicate a symbol that is a number **\
+    1 --> CIRTH_39
+    2 --> CIRTH_50
+    3 --> CIRTH_52
+    4 --> CIRTH_NUMERAL_4
+    5 --> CIRTH_22
+    6 --> CIRTH_39 CIRTH_39 CIRTH_39 CIRTH_39 CIRTH_39 CIRTH_39
+  \end
+
+\end

glaemresources/modes/english-futhorc.glaem

@@ -0,0 +1,114 @@
+\**
+
+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, adapted from old_english-futhorc.glaem"
+\end
+
+\language "English"
+\writing  "Runes"
+\mode     "English Futhorc based on the Hobbit"
+\version  "0.0.1"
+\authors  "J.R.R. Tolkien impl. David Fraser"
+
+\world      primary_related_to_arda
+\invention  jrrt
+
+\charset  unicode_runes true
+
+\beg options
+  \option use_aesc                        true
+  \** Thror's map uses separate S T anyway, and Tolkien's styling of this letter is different, so this is retained as an option but off by default **\
+  \option use_stan                        false
+\end
+
+
+\beg      preprocessor
+  \downcase
+\end
+
+\beg      processor
+
+  \beg    rules litteral
+    \** These rules generally follow https://ring-lord.tripod.com/runes/dwafrune.htm **\
+    f       --> FEOH \** There are variants with round and straight strokes; only the former is in the Unicode Runic range **\
+    (u,v)   --> URUZ \** There are variants with round and straight strokes; only the former is in the Unicode Runic range **\
+    th      --> THORN
+    oo      --> OS
+    o       --> OSfuvthooorcgwhnjipxzstbemlngeeda+ayeakquab
+    r       --> RAIDO
+    c       --> CEN
+    g       --> GEBO
+    w       --> WYNN
+    h       --> HAEGL
+    n       --> NAUD
+    (i,j)   --> IS
+    p       --> PEORTH \** This is the second variant; the variant that looks more like a K is not in the Unicode Runic range **\
+    x       --> EOLHX
+    z       --> CALC
+    s       --> RUNIC_LETTER_SH
+    t       --> TIR
+    \if use_stan
+      st  --> STAN 
+    \endif
+    b       --> BEORC
+    e       --> EH
+    m       --> MAN
+    l       --> LAGU
+    ng      --> ING
+    ee      --> ETHEL
+    d       --> DAEG \** Tolkien also uses an alternative with lines above and below, forming a box with a cross around it; this is not in the Unicode Runic range **\
+    \if use_aesc
+      a       --> AESC
+      +a      --> AC \** One of two alternatives in the chart; the other is not in Unicode Runic **\
+    \else
+      a       --> AC \** One of two alternatives in the chart; the other is not in Unicode Runic **\
+      +a      --> AESC
+    \endif
+    \** y       --> CIRTH_49 matches this letter correctly, but this is a problem, as no font has both CIRTH and RUNIC unicode block **\
+    y       --> YR \** This is the closest thing in unicode Runic to Tolkien's CIRTH_49 **\
+    ea      --> EAR
+    k       --> RUNIC_LETTER_FRANKS_CASKET_AC \** This is not an exact match but the closest in the Unicode Runic range **\
+    \** combinations **\
+    qu      --> CEN WYNN
+    \** in order to complete English orthography... however note that this mode is mostly direct transcription of letters... **\
+    q       --> CEN WYNN \** Assume a q is pronounced cw, even if not followed by a u **\
+  \end
+
+  \beg    rules  punctuation
+    , --> RUNIC_SINGLE_PUNCTUATION
+    ; --> RUNIC_SINGLE_PUNCTUATION
+    : --> RUNIC_MULTIPLE_PUNCTUATION
+    . --> RUNIC_MULTIPLE_PUNCTUATION
+    ! --> RUNIC_MULTIPLE_PUNCTUATION
+    ? --> RUNIC_CROSS_PUNCTUATION 
+    “ --> {NULL}
+    ” --> {NULL}
+    « --> {NULL}
+    » --> {NULL}
+    - --> {NULL}
+    ' --> {NULL}
+    " --> {NULL}
+  \end
+\end