glaemscribe 1.2.0 → 1.3.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/glaemscribe +2 -2
- data/glaemresources/charsets/cirth_ds.cst +514 -179
- data/glaemresources/charsets/eldamar.cst +210 -0
- data/glaemresources/charsets/tengwar_ds_annatar.cst +2776 -348
- data/glaemresources/charsets/tengwar_ds_eldamar.cst +2648 -351
- data/glaemresources/charsets/tengwar_ds_elfica.cst +2639 -346
- data/glaemresources/charsets/tengwar_ds_parmaite.cst +2648 -351
- data/glaemresources/charsets/tengwar_ds_sindarin.cst +2642 -348
- data/glaemresources/charsets/tengwar_freemono.cst +1 -1
- data/glaemresources/charsets/tengwar_guni_annatar.cst +2725 -300
- data/glaemresources/charsets/tengwar_guni_eldamar.cst +2589 -295
- data/glaemresources/charsets/tengwar_guni_elfica.cst +2592 -298
- data/glaemresources/charsets/tengwar_guni_parmaite.cst +2592 -297
- data/glaemresources/charsets/tengwar_guni_sindarin.cst +2591 -297
- data/glaemresources/charsets/tengwar_telcontar.cst +7 -0
- data/glaemresources/modes/blackspeech-tengwar-general_use.glaem +1 -1
- data/glaemresources/modes/english-cirth-espeak.glaem +687 -0
- data/glaemresources/modes/english-tengwar-espeak.glaem +814 -0
- data/glaemresources/modes/japanese-tengwar.glaem +9 -4
- data/glaemresources/modes/lang_belta-tengwar-dadef.glaem +248 -0
- data/glaemresources/modes/raw-cirth.glaem +154 -0
- data/lib/api/charset.rb +124 -57
- data/lib/api/charset_parser.rb +39 -26
- data/lib/api/mode.rb +35 -10
- data/lib/api/mode_parser.rb +21 -12
- data/lib/api/post_processor/outspace.rb +44 -0
- data/lib/api/post_processor/resolve_virtuals.rb +41 -19
- data/lib/api/rule_group.rb +1 -1
- data/lib/api/transcription_pre_post_processor.rb +51 -45
- data/lib/api/transcription_processor.rb +12 -9
- data/lib/glaemscribe.rb +2 -0
- data/lib_espeak/espeakng.for.glaemscribe.nowasm.sync.js +25 -11
- data/lib_espeak/glaemscribe_tts.js +363 -223
- metadata +12 -6
@@ -0,0 +1,210 @@
|
|
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
|
+
\version 0.0.1
|
26
|
+
|
27
|
+
\beg changelog
|
28
|
+
\entry "0.0.1" "Copy pasted from FreeMono charset."
|
29
|
+
\end
|
30
|
+
|
31
|
+
\char 20 SPACE
|
32
|
+
\char a0 NBSP
|
33
|
+
|
34
|
+
\** PUSTAR, take them in unicode not in personnal use (deprecation) **\
|
35
|
+
\char 2e31 PUNCT_DOT
|
36
|
+
\char 3a PUNCT_DDOT
|
37
|
+
\char 205D PUNCT_TDOT PUSTA_3
|
38
|
+
\char 2058 PUSTA_4
|
39
|
+
\char 10FB PUSTA_4_HALFED
|
40
|
+
\char 2E2C PUSTA_4_SQUARED
|
41
|
+
\char 2E2D PUSTA_5
|
42
|
+
|
43
|
+
\char e000 TW_11 TINCO
|
44
|
+
\char e001 TW_12 PARMA
|
45
|
+
\char e002 TW_13 CALMA
|
46
|
+
\char e003 TW_14 QUESSE
|
47
|
+
|
48
|
+
\char e004 TW_21 ANDO
|
49
|
+
\char e005 TW_22 UMBAR
|
50
|
+
\char e006 TW_23 ANGA
|
51
|
+
\char e007 TW_24 UNGWE
|
52
|
+
|
53
|
+
\char e008 TW_31 SULE THULE
|
54
|
+
\char e009 TW_32 FORMEN
|
55
|
+
\char e00A TW_33 AHA
|
56
|
+
\char e00B TW_34 HWESTA
|
57
|
+
|
58
|
+
\char e00C TW_41 ANTO
|
59
|
+
\char e00D TW_42 AMPA
|
60
|
+
\char e00E TW_43 ANCA
|
61
|
+
\char e00F TW_44 UNQUE
|
62
|
+
|
63
|
+
\char e010 TW_51 NUMEN
|
64
|
+
\char e011 TW_52 MALTA
|
65
|
+
\char e012 TW_53 NOLDO
|
66
|
+
\char e013 TW_54 NWALME
|
67
|
+
|
68
|
+
\char e014 TW_61 ORE
|
69
|
+
\char e015 TW_62 VALA
|
70
|
+
\char e016 TW_63 ANNA
|
71
|
+
\char e017 TW_64 VILYA
|
72
|
+
|
73
|
+
\char e018 TW_EXT_11 TINCO_EXT SULE_EXT THULE_EXT
|
74
|
+
\char e019 TW_EXT_12 PARMA_EXT FORMEN_EXT
|
75
|
+
\char e01A TW_EXT_13 CALMA_EXT AHA_EXT
|
76
|
+
\char e01B TW_EXT_14 QUESSE_EXT HWESTA_EXT
|
77
|
+
|
78
|
+
\char e01C TW_EXT_21 ANDO_EXT ANTO_EXT
|
79
|
+
\char e01D TW_EXT_22 UMBAR_EXT AMPA_EXT
|
80
|
+
\char e01E TW_EXT_23 ANGA_EXT ANCA_EXT
|
81
|
+
\char e01F TW_EXT_24 UNGWE_EXT UNQUE_EXT
|
82
|
+
|
83
|
+
\char e020 TW_71 ROMEN
|
84
|
+
\char e021 TW_72 ARDA
|
85
|
+
\char e022 TW_73 LAMBE
|
86
|
+
\char e023 TW_74 ALDA
|
87
|
+
|
88
|
+
\char e024 TW_81 SILME
|
89
|
+
\** Unfortunately, monotengwar is missing silme nuquerna used for y in beleriand **\
|
90
|
+
\char e025 TW_82 SILME_NUQUERNA SILME_NUQUERNA_ALT
|
91
|
+
\char e026 TW_83 ESSE
|
92
|
+
\char e027 TW_84 ESSE_NUQUERNA
|
93
|
+
|
94
|
+
\char e028 TW_91 HYARMEN
|
95
|
+
\char e029 TW_92 HWESTA_SINDARINWA
|
96
|
+
\char e02A TW_93 YANTA
|
97
|
+
\char e02B TW_94 URE
|
98
|
+
|
99
|
+
\char e02C ARA
|
100
|
+
\char e02D HALLA
|
101
|
+
\char e02E TELCO
|
102
|
+
\char e02F ?
|
103
|
+
|
104
|
+
\char e030 REVERSED_OSSE
|
105
|
+
\char e031 BOMBADIL_W
|
106
|
+
\char e032 OSSE
|
107
|
+
\char e033 ?
|
108
|
+
|
109
|
+
\char e034 LIGATING_SHORT_CARRIER
|
110
|
+
\char e035 ?
|
111
|
+
\char e036 ANNA_OPEN
|
112
|
+
\char e037 CHRISTOPHER_QU
|
113
|
+
|
114
|
+
\char e038 ?
|
115
|
+
\char e039 BOMBADIL_HW
|
116
|
+
\char e03A TW_MH MALTA_W_HOOK
|
117
|
+
\char e03B TW_MH_BELERIANDIC VALA_W_HOOK
|
118
|
+
|
119
|
+
\char e03C TW_HW_LOWDHAM HARP_SHAPED
|
120
|
+
\char e03D VAIA WAIA VAIYA
|
121
|
+
\char e03E ?
|
122
|
+
\char e03F ?
|
123
|
+
|
124
|
+
\char e040 A_TEHTA
|
125
|
+
\char e041 A_TEHTA_INF
|
126
|
+
\char e042 I_TEHTA_DOUBLE Y_TEHTA
|
127
|
+
\char e043 I_TEHTA_DOUBLE_INF PALATAL_SIGN Y_TEHTA_INF
|
128
|
+
|
129
|
+
\char e044 I_TEHTA
|
130
|
+
\char e045 I_TEHTA_INF NO_VOWEL_DOT UNUTIXE
|
131
|
+
\char e046 E_TEHTA
|
132
|
+
\char e047 E_TEHTA_INF
|
133
|
+
|
134
|
+
\char e048 E_TEHTA_DOUBLE
|
135
|
+
\char e049 E_TEHTA_DOUBLE_INF GEMINATE_DOUBLE
|
136
|
+
\char e04A O_TEHTA
|
137
|
+
\char e04B O_TEHTA_INF
|
138
|
+
|
139
|
+
\char e04C U_TEHTA
|
140
|
+
\char e04D U_TEHTA_INF
|
141
|
+
\char e04E O_TEHTA_DOUBLE
|
142
|
+
\char e04F U_TEHTA_DOUBLE
|
143
|
+
|
144
|
+
\char e050 NASALIZE_SIGN NASALIZE_SIGN_TILD
|
145
|
+
\char e051 GEMINATE_SIGN GEMINATE_SIGN_TILD
|
146
|
+
\char e052 WA_TEHTA SEV_TEHTA
|
147
|
+
\char e053 TEHTA_BREVE A_TEHTA_CIRCUM_REVERSED
|
148
|
+
|
149
|
+
\char e054 E_TEHTA_GRAVE
|
150
|
+
\char e055 A_TEHTA_CIRCUM
|
151
|
+
\char e056 A_TEHTA_REVERSED A_TEHTA_DOUBLE
|
152
|
+
\char e057 THINNAS THINF_STROKE
|
153
|
+
|
154
|
+
\** THE TWO FOLLOWING ONES ARE HIGHLY DISCUSSABLE, MAYBE WE SHOULD ADD A VIRTUAL CHAR FOR THESE **\
|
155
|
+
\char e058 SARINCE_ENDING_LONG SARINCE_FLOURISHED
|
156
|
+
\char e059 SARINCE COMBINING_SARINCE SHOOK_RIGHT_L SHOOK_LEFT_L
|
157
|
+
\char e05A ?
|
158
|
+
\char e05B ?
|
159
|
+
|
160
|
+
\char e065 PUNCT_EXCLAM
|
161
|
+
\char e066 PUNCT_INTERR
|
162
|
+
\char e067 ELVISH_PAREN PUNCT_PAREN_L PUNCT_PAREN_R PUNCT_PAREN_L_ALT PUNCT_PAREN_R_ALT BOOKMARK_SIGN
|
163
|
+
\char e068 PUNCT_TILD
|
164
|
+
|
165
|
+
\char e069 PUNCT_DTILD RING_MARK_L RING_MARK_R
|
166
|
+
|
167
|
+
\char e06A DQUOT_OPEN
|
168
|
+
\char e06B DQUOT_CLOSE
|
169
|
+
\char e06C THORIN_EXCLAMATION
|
170
|
+
|
171
|
+
\char e070 NUM_0
|
172
|
+
\char e071 NUM_1
|
173
|
+
\char e072 NUM_2
|
174
|
+
\char e073 NUM_3
|
175
|
+
\char e074 NUM_4
|
176
|
+
\char e075 NUM_5
|
177
|
+
\char e076 NUM_6
|
178
|
+
\char e077 NUM_7
|
179
|
+
\char e078 NUM_8
|
180
|
+
\char e079 NUM_9
|
181
|
+
\char e07A NUM_10
|
182
|
+
\char e07B NUM_11
|
183
|
+
\char e07C NUM_12
|
184
|
+
|
185
|
+
\char e07D CIRC_TEHTA_INF
|
186
|
+
|
187
|
+
\** Ligatured results are mapped here **\
|
188
|
+
\**
|
189
|
+
\char 10037 AHA_TINCO
|
190
|
+
\char 10038 HWESTA_TINCO
|
191
|
+
\char 10039 ANCA_CLOSED SILME_AHA
|
192
|
+
**\
|
193
|
+
|
194
|
+
\char 204A OLD_ENGLISH_AND
|
195
|
+
|
196
|
+
\char 200d ZWJ
|
197
|
+
|
198
|
+
\** Ligatured sequences used as one entity in modes **\
|
199
|
+
\beg seq AHA_TINCO
|
200
|
+
AHA ZWJ TINCO
|
201
|
+
\end
|
202
|
+
|
203
|
+
\beg seq HWESTA_TINCO
|
204
|
+
HWESTA ZWJ TINCO
|
205
|
+
\end
|
206
|
+
|
207
|
+
\beg seq ANCA_CLOSED SILME_AHA
|
208
|
+
SILME ZWJ AHA
|
209
|
+
\end
|
210
|
+
|