glaemscribe 1.1.14 → 1.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +5 -5
- data/bin/glaemscribe +21 -17
- data/glaemresources/charsets/cirth_ds.cst +540 -0
- data/glaemresources/charsets/eldamar.cst +210 -0
- data/glaemresources/charsets/sarati_eldamar.cst +256 -0
- data/glaemresources/charsets/tengwar_ds_annatar.cst +2868 -0
- data/glaemresources/charsets/tengwar_ds_eldamar.cst +2729 -0
- data/glaemresources/charsets/tengwar_ds_elfica.cst +2742 -0
- data/glaemresources/charsets/tengwar_ds_parmaite.cst +2726 -0
- data/glaemresources/charsets/tengwar_ds_sindarin.cst +2722 -0
- data/glaemresources/charsets/tengwar_freemono.cst +217 -0
- data/glaemresources/charsets/tengwar_guni_annatar.cst +2948 -0
- data/glaemresources/charsets/tengwar_guni_eldamar.cst +2809 -0
- data/glaemresources/charsets/tengwar_guni_elfica.cst +2809 -0
- data/glaemresources/charsets/tengwar_guni_parmaite.cst +2813 -0
- data/glaemresources/charsets/tengwar_guni_sindarin.cst +2808 -0
- data/glaemresources/charsets/tengwar_telcontar.cst +225 -0
- data/glaemresources/charsets/unicode_gothic.cst +64 -0
- data/glaemresources/charsets/unicode_runes.cst +121 -0
- data/glaemresources/modes/{adunaic.glaem → adunaic-tengwar-glaemscrafu.glaem} +14 -2
- data/glaemresources/modes/{blackspeech.glaem → blackspeech-tengwar-general_use.glaem} +13 -3
- data/glaemresources/modes/english-cirth-espeak.glaem +687 -0
- data/glaemresources/modes/english-tengwar-espeak.glaem +814 -0
- data/glaemresources/modes/japanese-tengwar.glaem +776 -0
- data/glaemresources/modes/{khuzdul.glaem → khuzdul-cirth-moria.glaem} +4 -1
- data/glaemresources/modes/lang_belta-tengwar-dadef.glaem +248 -0
- data/glaemresources/modes/{futhorc.glaem → old_english-futhorc.glaem} +0 -0
- data/glaemresources/modes/{mercian.glaem → old_english-tengwar-mercian.glaem} +22 -12
- data/glaemresources/modes/{westsaxon.glaem → old_english-tengwar-westsaxon.glaem} +20 -11
- data/glaemresources/modes/{futhark-runicus.glaem → old_norse-futhark-runicus.glaem} +0 -0
- data/glaemresources/modes/{futhark-younger.glaem → old_norse-futhark-younger.glaem} +0 -0
- data/glaemresources/modes/{quenya.glaem → quenya-tengwar-classical.glaem} +32 -50
- data/glaemresources/modes/raw-cirth.glaem +154 -0
- data/glaemresources/modes/raw-tengwar.glaem +46 -23
- data/glaemresources/modes/{rlyehian.glaem → rlyehian-tengwar.glaem} +14 -3
- data/glaemresources/modes/{sindarin-daeron.glaem → sindarin-cirth-daeron.glaem} +55 -14
- data/glaemresources/modes/{sindarin-beleriand.glaem → sindarin-tengwar-beleriand.glaem} +154 -28
- data/glaemresources/modes/{sindarin.glaem → sindarin-tengwar-general_use.glaem} +86 -25
- data/glaemresources/modes/{telerin.glaem → telerin-tengwar-glaemscrafu.glaem} +16 -6
- data/glaemresources/modes/{westron.glaem → westron-tengwar-glaemscrafu.glaem} +18 -8
- data/lib/api/charset.rb +67 -7
- data/lib/api/charset_parser.rb +14 -1
- data/lib/api/constants.rb +3 -4
- data/lib/api/fragment.rb +26 -5
- data/lib/api/if_tree.rb +70 -8
- data/lib/api/macro.rb +40 -0
- data/lib/api/mode.rb +66 -19
- data/lib/api/mode_parser.rb +117 -14
- data/lib/api/object_additions.rb +23 -1
- data/lib/api/option.rb +17 -2
- data/lib/api/post_processor/outspace.rb +44 -0
- data/lib/api/post_processor/resolve_virtuals.rb +25 -9
- data/lib/api/resource_manager.rb +1 -0
- data/lib/api/rule_group.rb +170 -26
- data/lib/api/sheaf_chain_iterator.rb +1 -1
- data/lib/api/transcription_pre_post_processor.rb +8 -5
- data/lib/api/transcription_processor.rb +15 -12
- data/lib/api/tts.rb +51 -0
- data/lib/glaemscribe.rb +36 -31
- data/lib_espeak/espeakng.for.glaemscribe.nowasm.sync.js +35 -0
- data/lib_espeak/glaemscribe_tts.js +505 -0
- metadata +76 -24
@@ -0,0 +1,217 @@
|
|
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
|
+
\** Charset for the FreeMonoTengwar font **\
|
26
|
+
|
27
|
+
\version 0.1.0
|
28
|
+
|
29
|
+
\beg changelog
|
30
|
+
\entry "0.0.5" "Added VALA_W_HOOK."
|
31
|
+
\entry "0.0.6" "Updating punctuation"
|
32
|
+
\entry "0.0.7" "Fixed missing tinco_ext / sule_ext"
|
33
|
+
\entry "0.0.8" "Added NBSP"
|
34
|
+
\entry "0.0.9" "Replaced fixed ligatures by their dynamic sequence"
|
35
|
+
\entry "0.1.0" "Added ELVISH_PAREN tokien, reworked sarince token names."
|
36
|
+
\end
|
37
|
+
|
38
|
+
\char 20 SPACE
|
39
|
+
\char a0 NBSP
|
40
|
+
|
41
|
+
\** PUSTAR, take them in unicode not in personnal use (deprecation) **\
|
42
|
+
\char 2e31 PUNCT_DOT
|
43
|
+
\char 3a PUNCT_DDOT
|
44
|
+
\char 205D PUNCT_TDOT PUSTA_3
|
45
|
+
\char 2058 PUSTA_4
|
46
|
+
\char 10FB PUSTA_4_HALFED
|
47
|
+
\char 2E2C PUSTA_4_SQUARED
|
48
|
+
\char 2E2D PUSTA_5
|
49
|
+
|
50
|
+
\char e000 TW_11 TINCO
|
51
|
+
\char e001 TW_12 PARMA
|
52
|
+
\char e002 TW_13 CALMA
|
53
|
+
\char e003 TW_14 QUESSE
|
54
|
+
|
55
|
+
\char e004 TW_21 ANDO
|
56
|
+
\char e005 TW_22 UMBAR
|
57
|
+
\char e006 TW_23 ANGA
|
58
|
+
\char e007 TW_24 UNGWE
|
59
|
+
|
60
|
+
\char e008 TW_31 SULE THULE
|
61
|
+
\char e009 TW_32 FORMEN
|
62
|
+
\char e00A TW_33 AHA
|
63
|
+
\char e00B TW_34 HWESTA
|
64
|
+
|
65
|
+
\char e00C TW_41 ANTO
|
66
|
+
\char e00D TW_42 AMPA
|
67
|
+
\char e00E TW_43 ANCA
|
68
|
+
\char e00F TW_44 UNQUE
|
69
|
+
|
70
|
+
\char e010 TW_51 NUMEN
|
71
|
+
\char e011 TW_52 MALTA
|
72
|
+
\char e012 TW_53 NOLDO
|
73
|
+
\char e013 TW_54 NWALME
|
74
|
+
|
75
|
+
\char e014 TW_61 ORE
|
76
|
+
\char e015 TW_62 VALA
|
77
|
+
\char e016 TW_63 ANNA
|
78
|
+
\char e017 TW_64 VILYA
|
79
|
+
|
80
|
+
\char e018 TW_EXT_11 TINCO_EXT SULE_EXT THULE_EXT
|
81
|
+
\char e019 TW_EXT_12 PARMA_EXT FORMEN_EXT
|
82
|
+
\char e01A TW_EXT_13 CALMA_EXT AHA_EXT
|
83
|
+
\char e01B TW_EXT_14 QUESSE_EXT HWESTA_EXT
|
84
|
+
|
85
|
+
\char e01C TW_EXT_21 ANDO_EXT ANTO_EXT
|
86
|
+
\char e01D TW_EXT_22 UMBAR_EXT AMPA_EXT
|
87
|
+
\char e01E TW_EXT_23 ANGA_EXT ANCA_EXT
|
88
|
+
\char e01F TW_EXT_24 UNGWE_EXT UNQUE_EXT
|
89
|
+
|
90
|
+
\char e020 TW_71 ROMEN
|
91
|
+
\char e021 TW_72 ARDA
|
92
|
+
\char e022 TW_73 LAMBE
|
93
|
+
\char e023 TW_74 ALDA
|
94
|
+
|
95
|
+
\char e024 TW_81 SILME
|
96
|
+
\** Unfortunately, monotengwar is missing silme nuquerna used for y in beleriand **\
|
97
|
+
\char e025 TW_82 SILME_NUQUERNA SILME_NUQUERNA_ALT
|
98
|
+
\char e026 TW_83 ESSE
|
99
|
+
\char e027 TW_84 ESSE_NUQUERNA
|
100
|
+
|
101
|
+
\char e028 TW_91 HYARMEN
|
102
|
+
\char e029 TW_92 HWESTA_SINDARINWA
|
103
|
+
\char e02A TW_93 YANTA
|
104
|
+
\char e02B TW_94 URE
|
105
|
+
|
106
|
+
\char e02C ARA
|
107
|
+
\char e02D HALLA
|
108
|
+
\char e02E TELCO
|
109
|
+
\char e02F ?
|
110
|
+
|
111
|
+
\char e030 REVERSED_OSSE
|
112
|
+
\char e031 BOMBADIL_W
|
113
|
+
\char e032 OSSE
|
114
|
+
\char e033 ?
|
115
|
+
|
116
|
+
\char e034 LIGATING_SHORT_CARRIER
|
117
|
+
\char e035 ?
|
118
|
+
\char e036 ANNA_OPEN
|
119
|
+
\char e037 CHRISTOPHER_QU
|
120
|
+
|
121
|
+
\char e038 ?
|
122
|
+
\char e039 BOMBADIL_HW
|
123
|
+
\char e03A TW_MH MALTA_W_HOOK
|
124
|
+
\char e03B TW_MH_BELERIANDIC VALA_W_HOOK
|
125
|
+
|
126
|
+
\char e03C TW_HW_LOWDHAM HARP_SHAPED
|
127
|
+
\char e03D VAIA WAIA VAIYA
|
128
|
+
\char e03E ?
|
129
|
+
\char e03F ?
|
130
|
+
|
131
|
+
\char e040 A_TEHTA
|
132
|
+
\char e041 A_TEHTA_INF
|
133
|
+
\char e042 I_TEHTA_DOUBLE Y_TEHTA
|
134
|
+
\char e043 I_TEHTA_DOUBLE_INF PALATAL_SIGN Y_TEHTA_INF
|
135
|
+
|
136
|
+
\char e044 I_TEHTA
|
137
|
+
\char e045 I_TEHTA_INF NO_VOWEL_DOT UNUTIXE
|
138
|
+
\char e046 E_TEHTA
|
139
|
+
\char e047 E_TEHTA_INF
|
140
|
+
|
141
|
+
\char e048 E_TEHTA_DOUBLE
|
142
|
+
\char e049 E_TEHTA_DOUBLE_INF GEMINATE_DOUBLE
|
143
|
+
\char e04A O_TEHTA
|
144
|
+
\char e04B O_TEHTA_INF
|
145
|
+
|
146
|
+
\char e04C U_TEHTA
|
147
|
+
\char e04D U_TEHTA_INF
|
148
|
+
\char e04E O_TEHTA_DOUBLE
|
149
|
+
\char e04F U_TEHTA_DOUBLE
|
150
|
+
|
151
|
+
\char e050 NASALIZE_SIGN NASALIZE_SIGN_TILD
|
152
|
+
\char e051 GEMINATE_SIGN GEMINATE_SIGN_TILD
|
153
|
+
\char e052 WA_TEHTA SEV_TEHTA
|
154
|
+
\char e053 TEHTA_BREVE A_TEHTA_CIRCUM_REVERSED
|
155
|
+
|
156
|
+
\char e054 E_TEHTA_GRAVE
|
157
|
+
\char e055 A_TEHTA_CIRCUM
|
158
|
+
\char e056 A_TEHTA_REVERSED A_TEHTA_DOUBLE
|
159
|
+
\char e057 THINNAS THINF_STROKE
|
160
|
+
|
161
|
+
\** THE TWO FOLLOWING ONES ARE HIGHLY DISCUSSABLE, MAYBE WE SHOULD ADD A VIRTUAL CHAR FOR THESE **\
|
162
|
+
\char e058 SARINCE_ENDING_LONG SARINCE_FLOURISHED
|
163
|
+
\char e059 SARINCE COMBINING_SARINCE SHOOK_RIGHT_L SHOOK_LEFT_L
|
164
|
+
\char e05A ?
|
165
|
+
\char e05B ?
|
166
|
+
|
167
|
+
\char e065 PUNCT_EXCLAM
|
168
|
+
\char e066 PUNCT_INTERR
|
169
|
+
\char e067 ELVISH_PAREN PUNCT_PAREN_L PUNCT_PAREN_R PUNCT_PAREN_L_ALT PUNCT_PAREN_R_ALT BOOKMARK_SIGN
|
170
|
+
\char e068 PUNCT_TILD
|
171
|
+
|
172
|
+
\char e069 PUNCT_DTILD RING_MARK_L RING_MARK_R
|
173
|
+
|
174
|
+
\char e06A DQUOT_OPEN
|
175
|
+
\char e06B DQUOT_CLOSE
|
176
|
+
\char e06C THORIN_EXCLAMATION
|
177
|
+
|
178
|
+
\char e070 NUM_0
|
179
|
+
\char e071 NUM_1
|
180
|
+
\char e072 NUM_2
|
181
|
+
\char e073 NUM_3
|
182
|
+
\char e074 NUM_4
|
183
|
+
\char e075 NUM_5
|
184
|
+
\char e076 NUM_6
|
185
|
+
\char e077 NUM_7
|
186
|
+
\char e078 NUM_8
|
187
|
+
\char e079 NUM_9
|
188
|
+
\char e07A NUM_10
|
189
|
+
\char e07B NUM_11
|
190
|
+
\char e07C NUM_12
|
191
|
+
|
192
|
+
\char e07D CIRC_TEHTA_INF
|
193
|
+
|
194
|
+
\** Ligatured results are mapped here **\
|
195
|
+
\**
|
196
|
+
\char 10037 AHA_TINCO
|
197
|
+
\char 10038 HWESTA_TINCO
|
198
|
+
\char 10039 ANCA_CLOSED SILME_AHA
|
199
|
+
**\
|
200
|
+
|
201
|
+
\char 204A OLD_ENGLISH_AND
|
202
|
+
|
203
|
+
\char 200d ZWJ
|
204
|
+
|
205
|
+
\** Ligatured sequences used as one entity in modes **\
|
206
|
+
\beg seq AHA_TINCO
|
207
|
+
AHA ZWJ TINCO
|
208
|
+
\end
|
209
|
+
|
210
|
+
\beg seq HWESTA_TINCO
|
211
|
+
HWESTA ZWJ TINCO
|
212
|
+
\end
|
213
|
+
|
214
|
+
\beg seq ANCA_CLOSED SILME_AHA
|
215
|
+
SILME ZWJ AHA
|
216
|
+
\end
|
217
|
+
|