glaemscribe 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/LICENSE.txt +19 -0
- data/bin/glaemscribe +307 -0
- data/glaemresources/charsets/cirth_ds.cst +205 -0
- data/glaemresources/charsets/sarati_eldamar.cst +256 -0
- data/glaemresources/charsets/tengwar_ds.cst +318 -0
- data/glaemresources/charsets/unicode_gothic.cst +64 -0
- data/glaemresources/charsets/unicode_runes.cst +120 -0
- data/glaemresources/modes/adunaic.glaem +251 -0
- data/glaemresources/modes/blackspeech-annatar.glaem +318 -0
- data/glaemresources/modes/blackspeech.glaem +260 -0
- data/glaemresources/modes/gothic.glaem +78 -0
- data/glaemresources/modes/khuzdul.glaem +141 -0
- data/glaemresources/modes/mercian.glaem +419 -0
- data/glaemresources/modes/oldnorse-medieval.glaem +127 -0
- data/glaemresources/modes/quenya-sarati.glaem +320 -0
- data/glaemresources/modes/quenya.glaem +307 -0
- data/glaemresources/modes/sindarin-beleriand.glaem +285 -0
- data/glaemresources/modes/sindarin-classical.glaem +276 -0
- data/glaemresources/modes/sindarin-daeron.glaem +182 -0
- data/glaemresources/modes/telerin.glaem +302 -0
- data/glaemresources/modes/valarin-sarati.glaem +210 -0
- data/glaemresources/modes/westron.glaem +340 -0
- data/glaemresources/modes/westsaxon.glaem +342 -0
- data/lib/api/charset.rb +84 -0
- data/lib/api/charset_parser.rb +55 -0
- data/lib/api/constants.rb +29 -0
- data/lib/api/debug.rb +36 -0
- data/lib/api/eval.rb +268 -0
- data/lib/api/fragment.rb +113 -0
- data/lib/api/glaeml.rb +200 -0
- data/lib/api/if_tree.rb +96 -0
- data/lib/api/mode.rb +112 -0
- data/lib/api/mode_parser.rb +314 -0
- data/lib/api/option.rb +64 -0
- data/lib/api/post_processor/reverse.rb +36 -0
- data/lib/api/pre_processor/downcase.rb +35 -0
- data/lib/api/pre_processor/elvish_numbers.rb +47 -0
- data/lib/api/pre_processor/rxsubstitute.rb +40 -0
- data/lib/api/pre_processor/substitute.rb +38 -0
- data/lib/api/pre_processor/up_down_tehta_split.rb +138 -0
- data/lib/api/resource_manager.rb +130 -0
- data/lib/api/rule.rb +99 -0
- data/lib/api/rule_group.rb +159 -0
- data/lib/api/sheaf.rb +70 -0
- data/lib/api/sheaf_chain.rb +86 -0
- data/lib/api/sheaf_chain_iterator.rb +108 -0
- data/lib/api/sub_rule.rb +40 -0
- data/lib/api/transcription_pre_post_processor.rb +118 -0
- data/lib/api/transcription_processor.rb +137 -0
- data/lib/api/transcription_tree_node.rb +91 -0
- data/lib/glaemscribe.rb +70 -0
- metadata +112 -0
@@ -0,0 +1,182 @@
|
|
1
|
+
\**
|
2
|
+
|
3
|
+
Glǽmscribe (also written Glaemscribe) is a software dedicated to
|
4
|
+
the transcription of texts between writing systems, and more
|
5
|
+
specifically dedicated to the transcription of J.R.R. Tolkien's
|
6
|
+
invented languages to some of his devised writing systems.
|
7
|
+
|
8
|
+
Copyright (C) 2015 Benjamin Babut (Talagan).
|
9
|
+
|
10
|
+
This program is free software: you can redistribute it and/or modify
|
11
|
+
it under the terms of the GNU Affero General Public License as published by
|
12
|
+
the Free Software Foundation, either version 3 of the License, or
|
13
|
+
any later version.
|
14
|
+
|
15
|
+
This program is distributed in the hope that it will be useful,
|
16
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
17
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
18
|
+
GNU Affero General Public License for more details.
|
19
|
+
|
20
|
+
You should have received a copy of the GNU Affero General Public License
|
21
|
+
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
22
|
+
|
23
|
+
**\
|
24
|
+
|
25
|
+
\** Sindarin Angerthas Daeron mode for glaemscribe **\
|
26
|
+
|
27
|
+
\language "Sindarin"
|
28
|
+
\writing "Cirth"
|
29
|
+
\mode "Angerthas Daeron"
|
30
|
+
\version "0.0.1"
|
31
|
+
\authors "Talagan (Benjamin Babut)"
|
32
|
+
|
33
|
+
\charset cirth_ds true
|
34
|
+
|
35
|
+
\beg preprocessor
|
36
|
+
\** Work exclusively downcase **\
|
37
|
+
\downcase
|
38
|
+
|
39
|
+
\** Simplify trema vowels **\
|
40
|
+
\substitute ä a
|
41
|
+
\substitute ë e
|
42
|
+
\substitute ï i
|
43
|
+
\substitute ö o
|
44
|
+
\substitute ü u
|
45
|
+
\substitute ÿ y
|
46
|
+
|
47
|
+
\** Dis-ambiguate long vowels **\
|
48
|
+
\rxsubstitute "(ā|â|aa)" "á"
|
49
|
+
\rxsubstitute "(ē|ê|ee)" "é"
|
50
|
+
\rxsubstitute "(ī|î|ii)" "í"
|
51
|
+
\rxsubstitute "(ō|ô|oo)" "ó"
|
52
|
+
\rxsubstitute "(ū|û|uu)" "ú"
|
53
|
+
\rxsubstitute "(ȳ|ŷ|yy)" "ý"
|
54
|
+
\end
|
55
|
+
|
56
|
+
\beg processor
|
57
|
+
|
58
|
+
\** We redefine the output space to have something beautiful, especially with erebor1 and erebor2 **\
|
59
|
+
\outspace CIRTH_SPACE_BIG
|
60
|
+
|
61
|
+
\beg rules litteral
|
62
|
+
a --> CIRTH_48
|
63
|
+
á --> CIRTH_49
|
64
|
+
|
65
|
+
b --> CIRTH_2
|
66
|
+
bh --> CIRTH_4
|
67
|
+
c --> CIRTH_18
|
68
|
+
ch --> CIRTH_13
|
69
|
+
|
70
|
+
d --> CIRTH_9
|
71
|
+
|
72
|
+
dh --> CIRTH_11
|
73
|
+
đ --> CIRTH_11
|
74
|
+
ð --> CIRTH_11
|
75
|
+
ðh --> CIRTH_11
|
76
|
+
|
77
|
+
e --> CIRTH_46
|
78
|
+
é --> CIRTH_47
|
79
|
+
|
80
|
+
f --> CIRTH_3
|
81
|
+
ff_ --> CIRTH_3
|
82
|
+
|
83
|
+
g --> CIRTH_19
|
84
|
+
gh --> CIRTH_21
|
85
|
+
ghw --> CIRTH_26
|
86
|
+
gw --> CIRTH_24
|
87
|
+
h --> CIRTH_5 \** . is another one??, V is +h (should be used in combinations, maybe todo) **\
|
88
|
+
i --> CIRTH_39
|
89
|
+
í --> CIRTH_39 CIRTH_39
|
90
|
+
j --> CIRTH_14
|
91
|
+
k --> CIRTH_18
|
92
|
+
kh --> CIRTH_20
|
93
|
+
khw --> CIRTH_25
|
94
|
+
kw --> CIRTH_23
|
95
|
+
l --> CIRTH_31
|
96
|
+
lh --> CIRTH_32
|
97
|
+
m --> CIRTH_6
|
98
|
+
mb --> CIRTH_7
|
99
|
+
mh --> CIRTH_7
|
100
|
+
n --> CIRTH_12
|
101
|
+
nc_ --> CIRTH_22 CIRTH_18 \** equals ŋc **\
|
102
|
+
nd --> CIRTH_38
|
103
|
+
ng --> CIRTH_33
|
104
|
+
|
105
|
+
_ng --> CIRTH_22
|
106
|
+
ng_ --> CIRTH_22
|
107
|
+
ŋ --> CIRTH_22
|
108
|
+
|
109
|
+
nw --> CIRTH_28
|
110
|
+
ngw --> CIRTH_27
|
111
|
+
nj --> CIRTH_17
|
112
|
+
o --> CIRTH_50
|
113
|
+
ó --> CIRTH_51 \** Can use CIRTH_51_ALT **\
|
114
|
+
ö --> CIRTH_52 \** Can use CIRTH_52_ALT **\
|
115
|
+
œ --> CIRTH_52
|
116
|
+
p --> CIRTH_1
|
117
|
+
r --> CIRTH_29
|
118
|
+
rh --> CIRTH_30
|
119
|
+
s --> CIRTH_34 \** Can use CIRTH_35 **\
|
120
|
+
sh --> CIRTH_15
|
121
|
+
ss --> CIRTH_36
|
122
|
+
t --> CIRTH_8
|
123
|
+
th --> CIRTH_10
|
124
|
+
u --> CIRTH_42
|
125
|
+
ú --> CIRTH_43
|
126
|
+
ü --> CIRTH_45_ALT \** Can use CIRTH_45 **\
|
127
|
+
y --> CIRTH_45_ALT \** Can use CIRTH_45 **\
|
128
|
+
v --> CIRTH_4
|
129
|
+
w --> CIRTH_44
|
130
|
+
zh --> CIRTH_16
|
131
|
+
\end
|
132
|
+
|
133
|
+
\beg rules punctuation
|
134
|
+
|
135
|
+
. --> CIRTH_PUNCT_THREE_DOTS
|
136
|
+
.. --> CIRTH_PUNCT_THREE_DOTS
|
137
|
+
... --> CIRTH_PUNCT_THREE_DOTS
|
138
|
+
… --> CIRTH_PUNCT_THREE_DOTS
|
139
|
+
.... --> CIRTH_PUNCT_THREE_DOTS
|
140
|
+
..... --> CIRTH_PUNCT_THREE_DOTS
|
141
|
+
...... --> CIRTH_PUNCT_THREE_DOTS
|
142
|
+
....... --> CIRTH_PUNCT_THREE_DOTS
|
143
|
+
|
144
|
+
, --> CIRTH_PUNCT_MID_DOT
|
145
|
+
: --> CIRTH_PUNCT_TWO_DOTS
|
146
|
+
; --> CIRTH_PUNCT_TWO_DOTS
|
147
|
+
! --> CIRTH_PUNCT_THREE_DOTS
|
148
|
+
? --> CIRTH_PUNCT_THREE_DOTS
|
149
|
+
· --> {NULL}
|
150
|
+
|
151
|
+
- --> {NULL}
|
152
|
+
– --> CIRTH_PUNCT_TWO_DOTS
|
153
|
+
— --> CIRTH_PUNCT_TWO_DOTS
|
154
|
+
|
155
|
+
\** Apostrophe **\
|
156
|
+
|
157
|
+
' --> {NULL}
|
158
|
+
’ --> {NULL}
|
159
|
+
|
160
|
+
\** Quotes **\
|
161
|
+
|
162
|
+
“ --> {NULL}
|
163
|
+
” --> {NULL}
|
164
|
+
« --> {NULL}
|
165
|
+
» --> {NULL}
|
166
|
+
|
167
|
+
[ --> CIRTH_PUNCT_THREE_DOTS_L
|
168
|
+
] --> CIRTH_PUNCT_THREE_DOTS_L
|
169
|
+
( --> CIRTH_PUNCT_THREE_DOTS_L
|
170
|
+
) --> CIRTH_PUNCT_THREE_DOTS_L
|
171
|
+
{ --> CIRTH_PUNCT_THREE_DOTS_L
|
172
|
+
} --> CIRTH_PUNCT_THREE_DOTS_L
|
173
|
+
< --> CIRTH_PUNCT_THREE_DOTS_L
|
174
|
+
> --> CIRTH_PUNCT_THREE_DOTS_L
|
175
|
+
|
176
|
+
/ --> CIRTH_PUNCT_FOUR_DOTS
|
177
|
+
|
178
|
+
\end
|
179
|
+
\end
|
180
|
+
|
181
|
+
|
182
|
+
|
@@ -0,0 +1,302 @@
|
|
1
|
+
\**
|
2
|
+
|
3
|
+
Glǽmscribe (also written Glaemscribe) is a software dedicated to
|
4
|
+
the transcription of texts between writing systems, and more
|
5
|
+
specifically dedicated to the transcription of J.R.R. Tolkien's
|
6
|
+
invented languages to some of his devised writing systems.
|
7
|
+
|
8
|
+
Copyright (C) 2015 Benjamin Babut (Talagan).
|
9
|
+
|
10
|
+
This program is free software: you can redistribute it and/or modify
|
11
|
+
it under the terms of the GNU Affero General Public License as published by
|
12
|
+
the Free Software Foundation, either version 3 of the License, or
|
13
|
+
any later version.
|
14
|
+
|
15
|
+
This program is distributed in the hope that it will be useful,
|
16
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
17
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
18
|
+
GNU Affero General Public License for more details.
|
19
|
+
|
20
|
+
You should have received a copy of the GNU Affero General Public License
|
21
|
+
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
22
|
+
|
23
|
+
**\
|
24
|
+
|
25
|
+
\** Telerin mode for glaemscribe (MAY BE INCOMPLETE) - Derived from Quenya **\
|
26
|
+
|
27
|
+
\language "Telerin"
|
28
|
+
\writing "Tengwar"
|
29
|
+
\mode "Glaemscrafu"
|
30
|
+
\version "0.0.1"
|
31
|
+
\authors "Talagan (Benjamin Babut)"
|
32
|
+
|
33
|
+
\charset tengwar_ds true
|
34
|
+
|
35
|
+
\beg options
|
36
|
+
\option reverse_numbers true
|
37
|
+
\beg option numbers_base BASE_12
|
38
|
+
\value BASE_10 10
|
39
|
+
\value BASE_12 12
|
40
|
+
\end
|
41
|
+
\end
|
42
|
+
|
43
|
+
\beg preprocessor
|
44
|
+
\** Work exclusively downcase **\
|
45
|
+
\downcase
|
46
|
+
|
47
|
+
\** Simplify trema vowels **\
|
48
|
+
\substitute ä a
|
49
|
+
\substitute ë e
|
50
|
+
\substitute ï i
|
51
|
+
\substitute ö o
|
52
|
+
\substitute ü u
|
53
|
+
\substitute ÿ y
|
54
|
+
|
55
|
+
\** Dis-ambiguate long vowels **\
|
56
|
+
\rxsubstitute "(ā|â|aa)" "á"
|
57
|
+
\rxsubstitute "(ē|ê|ee)" "é"
|
58
|
+
\rxsubstitute "(ī|î|ii)" "í"
|
59
|
+
\rxsubstitute "(ō|ô|oo)" "ó"
|
60
|
+
\rxsubstitute "(ū|û|uu)" "ú"
|
61
|
+
\rxsubstitute "(ȳ|ŷ|yy)" "ý"
|
62
|
+
|
63
|
+
\substitute "qu" "q" \** Dis-ambiguate qu **\
|
64
|
+
|
65
|
+
\elvish_numbers "\\eval numbers_base" "\\eval reverse_numbers"
|
66
|
+
\end
|
67
|
+
|
68
|
+
\beg processor
|
69
|
+
|
70
|
+
\beg rules litteral
|
71
|
+
{A} === a
|
72
|
+
{AA} === á
|
73
|
+
{E} === e
|
74
|
+
{EE} === é
|
75
|
+
{I} === i
|
76
|
+
{II} === í
|
77
|
+
{O} === o
|
78
|
+
{OO} === ó
|
79
|
+
{U} === u
|
80
|
+
{UU} === ú
|
81
|
+
|
82
|
+
{AI} === {A}{I}
|
83
|
+
{AU} === {A}{U}
|
84
|
+
{EU} === {E}{U}
|
85
|
+
{IU} === {I}{U}
|
86
|
+
{OI} === {O}{I}
|
87
|
+
{UI} === {U}{I}
|
88
|
+
|
89
|
+
|
90
|
+
{K} === (c,k)
|
91
|
+
{W} === (v,w)
|
92
|
+
{SS} === (z,ss)
|
93
|
+
|
94
|
+
\** {MB} === (b,mb) **\
|
95
|
+
\** {SS} === (z,ss) **\
|
96
|
+
|
97
|
+
{VOWELS} === {A} * {E} * {I} * {O} * {U}
|
98
|
+
{LVOWELS} === {AA} * {EE} * {II} * {OO} * {UU}
|
99
|
+
|
100
|
+
{TEHTA_XS} === A_TEHTA_XS * E_TEHTA_XS * I_TEHTA_XS * O_TEHTA_XS * U_TEHTA_XS
|
101
|
+
{TEHTA__S} === A_TEHTA_S * E_TEHTA_S * I_TEHTA_S * O_TEHTA_S * U_TEHTA_S
|
102
|
+
{TEHTA__L} === A_TEHTA_L * E_TEHTA_L * I_TEHTA_L * O_TEHTA_L * U_TEHTA_L
|
103
|
+
{TEHTA_XL} === A_TEHTA_XL * E_TEHTA_XL * I_TEHTA_XL * O_TEHTA_XL * U_TEHTA_XL
|
104
|
+
|
105
|
+
{DIPHTHONGS} === {AI} * {AU} * {EU} * {IU} * {OI} * {UI}
|
106
|
+
{DIPHTHENGS} === YANTA A_TEHTA_L * URE A_TEHTA_L * URE E_TEHTA_L * URE I_TEHTA_L * YANTA O_TEHTA_L * YANTA U_TEHTA_L
|
107
|
+
|
108
|
+
|
109
|
+
{V_D_KER} === [ {VOWELS} * {DIPHTHONGS} ]
|
110
|
+
{V_D_IMG_XS} === [ {TEHTA_XS} * {DIPHTHENGS} ]
|
111
|
+
{V_D_IMG__S} === [ {TEHTA__L} * {DIPHTHENGS} ]
|
112
|
+
{V_D_IMG__L} === [ {TEHTA__S} * {DIPHTHENGS} ]
|
113
|
+
{V_D_IMG_XL} === [ {TEHTA_XL} * {DIPHTHENGS} ]
|
114
|
+
|
115
|
+
{V_D_KER_WN} === [ {VOWELS} * {DIPHTHONGS} * {NULL} ]
|
116
|
+
{V_D_IMG_XS_WN} === [ {TEHTA_XS} * {DIPHTHENGS} * {NULL} ]
|
117
|
+
{V_D_IMG__S_WN} === [ {TEHTA__L} * {DIPHTHENGS} * {NULL} ]
|
118
|
+
{V_D_IMG__L_WN} === [ {TEHTA__S} * {DIPHTHENGS} * {NULL} ]
|
119
|
+
{V_D_IMG_XL_WN} === [ {TEHTA_XL} * {DIPHTHENGS} * {NULL} ]
|
120
|
+
|
121
|
+
\** VOWEL RULES **\
|
122
|
+
[{VOWELS}] --> TELCO[{TEHTA_XS}] \** Replace isolated short vowels **\
|
123
|
+
[{LVOWELS}] --> ARA[{TEHTA_XS}] \** Replace long vowels **\
|
124
|
+
[{DIPHTHONGS}] --> [{DIPHTHENGS}] \** Replace diphthongs **\
|
125
|
+
|
126
|
+
\** TELERIN: changed v/w, removed all y rules **\
|
127
|
+
|
128
|
+
\** ===================== **\
|
129
|
+
\** 1ST LINE RULES **\
|
130
|
+
\** ===================== **\
|
131
|
+
{L1_KER_1} === t * p
|
132
|
+
{L1_IMG_1} === TINCO * PARMA
|
133
|
+
{L1_KER_2} === {K} * q
|
134
|
+
{L1_IMG_2} === CALMA * QUESSE
|
135
|
+
{L1_KER_1_GEMS} === tt * pp
|
136
|
+
{L1_IMG_1_GEMS} === TINCO DASH_INF_S * PARMA DASH_INF_S
|
137
|
+
|
138
|
+
\** NORMAL **\
|
139
|
+
[ {L1_KER_1} ] {V_D_KER_WN} --> [ {L1_IMG_1} ] {V_D_IMG__S_WN}
|
140
|
+
[ {L1_KER_2} ] {V_D_KER_WN} --> [ {L1_IMG_2} ] {V_D_IMG__S_WN}
|
141
|
+
|
142
|
+
\** GEMINATED **\
|
143
|
+
[ {L1_KER_1_GEMS} ] {V_D_KER_WN} --> [ {L1_IMG_1_GEMS} ] {V_D_IMG__S_WN} \** Tengscribe uses S but L is probably better **\
|
144
|
+
{K}{K}{V_D_KER_WN} --> CALMA DASH_INF_S {V_D_IMG__S_WN}
|
145
|
+
|
146
|
+
ts{V_D_KER_WN}_ --> TINCO SHOOK_RIGHT_L {V_D_IMG__S_WN}
|
147
|
+
ps{V_D_KER_WN}_ --> PARMA SHOOK_RIGHT_L {V_D_IMG__S_WN}
|
148
|
+
x{V_D_KER_WN} --> CALMA SHOOK_LEFT_L {V_D_IMG__S_WN} \** render ks for x **\
|
149
|
+
|
150
|
+
\** ===================== **\
|
151
|
+
\** 2ND LINE RULES **\
|
152
|
+
\** ===================== **\
|
153
|
+
{L2_KER} === nd * mb * ng * ngw
|
154
|
+
{L2_IMG} === ANDO * UMBAR * ANGA * UNGWE
|
155
|
+
|
156
|
+
\** STANDARD **\
|
157
|
+
[{L2_KER}]{V_D_KER_WN} --> [{L2_IMG}]{V_D_IMG_XL_WN}
|
158
|
+
|
159
|
+
{L2_KER_2} === d * b * g
|
160
|
+
{L2_IMG_2} === ORE * VALA * ANNA
|
161
|
+
|
162
|
+
\** STANDARD **\
|
163
|
+
[{L2_KER_2}]{V_D_KER_WN} --> [{L2_IMG_2}]{V_D_IMG__S_WN}
|
164
|
+
|
165
|
+
\** ===================== **\
|
166
|
+
\** 3RD LINE RULES **\
|
167
|
+
\** ===================== **\
|
168
|
+
{L3_KER_1} === th * f
|
169
|
+
{L3_IMG_1} === SULE * FORMEN
|
170
|
+
{L3_KER_2} === h * hw
|
171
|
+
{L3_IMG_2} === AHA * HWESTA
|
172
|
+
|
173
|
+
\** NORMAL **\
|
174
|
+
[{L3_KER_1}]{V_D_KER_WN} --> [{L3_IMG_1}]{V_D_IMG__S_WN}
|
175
|
+
[{L3_KER_2}]{V_D_KER_WN} --> [{L3_IMG_2}]{V_D_IMG__S_WN} \** Tengscribe uses S but L is probably better **\
|
176
|
+
|
177
|
+
\** Override h with vowels (descendent) **\
|
178
|
+
_h{V_D_KER} --> HYARMEN {V_D_IMG__L}
|
179
|
+
h[{LVOWELS}] --> HYARMEN ARA [{TEHTA_XS}]
|
180
|
+
h --> AHA
|
181
|
+
|
182
|
+
\** ===================== **\
|
183
|
+
\** 4TH LINE RULES **\
|
184
|
+
\** ===================== **\
|
185
|
+
{L4_KER} === nt * mp * nc * nq \** Not nqu, due to preprocessor **\
|
186
|
+
{L4_IMG} === ANTO * AMPA * ANCA * UNQUE
|
187
|
+
|
188
|
+
\** NORMAL **\
|
189
|
+
[{L4_KER}]{V_D_KER_WN} --> [{L4_IMG}]{V_D_IMG_XL_WN}
|
190
|
+
|
191
|
+
\** ===================== **\
|
192
|
+
\** 5TH LINE RULES **\
|
193
|
+
\** ===================== **\
|
194
|
+
{L5_KER} === n * m * ñ * ñw * _nw
|
195
|
+
{L5_IMG} === NUMEN * MALTA * NOLDO * NWALME * NWALME
|
196
|
+
|
197
|
+
[{L5_KER}]{V_D_KER_WN} --> [{L5_IMG}]{V_D_IMG_XL_WN}
|
198
|
+
|
199
|
+
nn{V_D_KER_WN} --> NUMEN DASH_INF_L {V_D_IMG_XL_WN}
|
200
|
+
mm{V_D_KER_WN} --> MALTA DASH_INF_L {V_D_IMG_XL_WN}
|
201
|
+
|
202
|
+
\** ===================== **\
|
203
|
+
\** 6TH LINE RULES **\
|
204
|
+
\** ===================== **\
|
205
|
+
{L6_KER} === r * {W}
|
206
|
+
{L6_IMG} === ROMEN * VILYA
|
207
|
+
|
208
|
+
[{L6_KER}]{V_D_KER_WN} --> [{L6_IMG}]{V_D_IMG__S_WN}
|
209
|
+
|
210
|
+
rr{V_D_KER_WN} --> ROMEN DASH_INF_S {V_D_IMG__S_WN}
|
211
|
+
rd{V_D_KER_WN} --> ARDA {V_D_IMG__S_WN}
|
212
|
+
|
213
|
+
\** ===================== **\
|
214
|
+
\** L LINE RULES **\
|
215
|
+
\** ===================== **\
|
216
|
+
{LINE_L_KER} === l * ld * ll
|
217
|
+
{LINE_L_IMG} === LAMBE * ALDA * LAMBE LAMBE_MARK_TILD
|
218
|
+
|
219
|
+
[{LINE_L_KER}]{V_D_KER_WN} --> [{LINE_L_IMG}]{V_D_IMG__S_WN}
|
220
|
+
hl{V_D_KER_WN} --> HALLA LAMBE {V_D_IMG__S_WN}
|
221
|
+
hr{V_D_KER_WN} --> HALLA ROMEN {V_D_IMG__S_WN}
|
222
|
+
|
223
|
+
\** ===================== **\
|
224
|
+
\** S/Z LINE RULES **\
|
225
|
+
\** ===================== **\
|
226
|
+
{L8_KER} === s * {SS}
|
227
|
+
{L8_IMG} === SILME_NUQUERNA * ESSE_NUQUERNA
|
228
|
+
|
229
|
+
[{L8_KER}]{V_D_KER_WN} --> [{L8_IMG}]{V_D_IMG__S_WN}
|
230
|
+
|
231
|
+
\** Override lonely s / ss / before consonant **\
|
232
|
+
s --> SILME
|
233
|
+
s[{LVOWELS}] --> SILME ARA [{TEHTA_XS}]
|
234
|
+
{SS} --> ESSE
|
235
|
+
{SS}[{LVOWELS}] --> ESSE ARA [{TEHTA_XS}]
|
236
|
+
\end
|
237
|
+
|
238
|
+
\beg rules punctuation
|
239
|
+
. --> PUNCT_DDOT
|
240
|
+
.. --> PUNCT_DOT PUNCT_DDOT PUNCT_DOT
|
241
|
+
… --> PUNCT_TILD
|
242
|
+
... --> PUNCT_TILD
|
243
|
+
.... --> PUNCT_TILD
|
244
|
+
..... --> PUNCT_TILD
|
245
|
+
...... --> PUNCT_TILD
|
246
|
+
....... --> PUNCT_TILD
|
247
|
+
|
248
|
+
, --> PUNCT_DOT
|
249
|
+
: --> PUNCT_DOT
|
250
|
+
; --> PUNCT_DOT
|
251
|
+
! --> PUNCT_EXCLAM
|
252
|
+
? --> PUNCT_INTERR
|
253
|
+
· --> PUNCT_DOT
|
254
|
+
|
255
|
+
\** Apostrophe **\
|
256
|
+
|
257
|
+
' --> {NULL}
|
258
|
+
’ --> {NULL}
|
259
|
+
|
260
|
+
\** Quotes **\
|
261
|
+
|
262
|
+
“ --> DQUOT_OPEN
|
263
|
+
” --> DQUOT_CLOSE
|
264
|
+
« --> DQUOT_OPEN
|
265
|
+
» --> DQUOT_CLOSE
|
266
|
+
|
267
|
+
- --> {NULL}
|
268
|
+
– --> PUNCT_TILD
|
269
|
+
— --> PUNCT_TILD
|
270
|
+
|
271
|
+
[ --> PUNCT_PAREN_L
|
272
|
+
] --> PUNCT_PAREN_R
|
273
|
+
( --> PUNCT_PAREN_L
|
274
|
+
) --> PUNCT_PAREN_R
|
275
|
+
{ --> PUNCT_PAREN_L
|
276
|
+
} --> PUNCT_PAREN_R
|
277
|
+
< --> PUNCT_PAREN_L
|
278
|
+
> --> PUNCT_PAREN_R
|
279
|
+
|
280
|
+
\** Not universal between fonts ... **\
|
281
|
+
$ --> BOOKMARK_SIGN
|
282
|
+
≤ --> RING_MARK_L \** Ring inscription left beautiful stuff **\
|
283
|
+
≥ --> RING_MARK_R \** Ring inscription right beautiful stuff **\
|
284
|
+
|
285
|
+
\end
|
286
|
+
|
287
|
+
\beg rules numbers
|
288
|
+
0 --> NUM_0
|
289
|
+
1 --> NUM_1
|
290
|
+
2 --> NUM_2
|
291
|
+
3 --> NUM_3
|
292
|
+
4 --> NUM_4
|
293
|
+
5 --> NUM_5
|
294
|
+
6 --> NUM_6
|
295
|
+
7 --> NUM_7
|
296
|
+
8 --> NUM_8
|
297
|
+
9 --> NUM_9
|
298
|
+
A --> NUM_10
|
299
|
+
B --> NUM_11
|
300
|
+
\end
|
301
|
+
\end
|
302
|
+
|