interscript-maps 3.2.4 → 3.3.0
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 +4 -4
- data/interscript-maps.gemspec +1 -1
- data/maps/alalc-aze-Cyrl-Latn-1997.isc +48 -11
- data/maps/alalc-ben-Beng-Latn-2017.isc +68 -17
- data/maps/alalc-sat-Olck-Latn-2017.isc +7 -3
- data/maps/bsi-rus-Cyrl-Latn-2979-1958.isc +233 -0
- data/maps/din-ab-Cyrl-Latn-1460-2-2011.isc +8 -4
- data/maps/din-atv-Cyrl-Latn-1460-2-2011.isc +8 -4
- data/maps/din-az-Cyrl-Latn-1460-2-2011.isc +10 -6
- data/maps/din-ba-Cyrl-Latn-1460-2-2011.isc +10 -6
- data/maps/din-urd-Arab-Latn-31635-2011.isc +7 -1
- data/maps/iso-ben-Beng-Latn-15919-2001.isc +5 -0
- data/maps/iso-ben-Beng-Latn-15919-2026.isc +228 -0
- data/maps/iso-doi-Takr-Latn-15919-2026.isc +182 -0
- data/maps/iso-guj-Gujr-Latn-15919-2026.isc +231 -0
- data/maps/iso-heb-Hebr-Latn-259-1984.isc +426 -0
- data/maps/iso-heb-Hebr-Latn-259-2-1994.isc +469 -0
- data/maps/iso-inc-Kthi-Latn-15919-2001.isc +121 -0
- data/maps/iso-inc-Kthi-Latn-15919-2026.isc +197 -0
- data/maps/iso-jpn-Hrkt-Latn-3602-1989.isc +53 -0
- data/maps/iso-kan-Kana-Latn-15919-2001.isc +8 -4
- data/maps/iso-kan-Kana-Latn-15919-2026.isc +229 -0
- data/maps/iso-kas-Shrd-Latn-15919-2026.isc +208 -0
- data/maps/iso-mal-Mlym-Latn-15919-2001.isc +1 -0
- data/maps/iso-mal-Mlym-Latn-15919-2026.isc +223 -0
- data/maps/iso-mar-Deva-Latn-15919-2001.isc +1 -1
- data/maps/iso-mar-Modi-Latn-15919-2026.isc +204 -0
- data/maps/iso-new-Newa-Latn-15919-2026.isc +221 -0
- data/maps/iso-ori-Orya-Latn-15919-2026.isc +222 -0
- data/maps/iso-pan-Guru-Latn-15919-2026.isc +222 -0
- data/maps/iso-pra-Brah-Latn-15919-2026.isc +231 -0
- data/maps/iso-san-Deva-Latn-15919-2001.isc +5 -2
- data/maps/iso-san-Deva-Latn-15919-2026.isc +278 -0
- data/maps/iso-san-Gran-Latn-15919-2026.isc +208 -0
- data/maps/iso-sin-Sinh-Latn-15919-2001.isc +174 -0
- data/maps/iso-sin-Sinh-Latn-15919-2026.isc +238 -0
- data/maps/iso-tam-Taml-Latn-15919-2001.isc +1 -0
- data/maps/iso-tam-Taml-Latn-15919-2026.isc +178 -0
- data/maps/iso-tel-Telu-Latn-15919-2001.isc +7 -0
- data/maps/iso-tel-Telu-Latn-15919-2026.isc +229 -0
- data/maps/odni-che-Cyrl-Latn-2015.isc +19 -19
- data/maps/odni-mkd-Cyrl-Latn-2015.isc +11 -16
- data/maps/var-jpn-Hrkt-Latn-komaba-2009.isc +417 -0
- metadata +24 -2
- data/maps/bsi-rus-Cyrl-Latn-1958.isc +0 -199
|
@@ -0,0 +1,417 @@
|
|
|
1
|
+
system "VAR:jpn-Hrkt:Latn:komaba-2009" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id var
|
|
5
|
+
id komaba-2009
|
|
6
|
+
language iso-639-2:jpn
|
|
7
|
+
source_script Hrkt
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "Recommended System for Romanizing Japanese (UT-Komaba, 2009)"
|
|
10
|
+
url http://park.itc.u-tokyo.ac.jp/eigo/romaji.html
|
|
11
|
+
creation_date 2009
|
|
12
|
+
description { The Hepburn-based romanization recommended by the Department of
|
|
13
|
+
English Language / Komaba Organization for Educational Development,
|
|
14
|
+
The University of Tokyo, Komaba ("Recommended System for Romanizing
|
|
15
|
+
Japanese", 2009.04 v1).
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
notes {
|
|
19
|
+
note "Syllabic n is always n, never m before b/p/m (tonbo, shinpai, sanma); before a vowel or y in the same word it takes a following apostrophe (hon%s i, hon%s yaku), which distinguishes honyu (honyu) from honyu (hon%s yu)." % (APOS, APOS, APOS)
|
|
20
|
+
note "Long consonants (small tsu) double the following consonant letter; before ch-syllables the small tsu is written as a single t (atchaku, not attchaku); before sh it doubles as s (asshuku); before ts it doubles as t (yottsu)."
|
|
21
|
+
note "Long vowels are indicated with a macron (okāsan, kīkī, kūkai, kēki, tōri, kōzō); the ei row of kana (kei, sei, mei...) is spelled out as ei even though pronounced with the vowel sequence of a long e (keizai, seifu, mein)."
|
|
22
|
+
note "Vowel-length limitation (same as the corpus hepburn-1886 note): morpheme-boundary vowel sequences that the document requires to be repeated rather than macronized (baai, Kiihanto, Katsuura, Ise Eki, kouta) cannot be detected from kana alone; this map collapses same-vowel kana pairs to the macron by default and the repeated spellings require lexical pre-segmentation. The lengthening bar is transcribed by a macron on the preceding vowel."
|
|
23
|
+
note "The document prints the fa row as fa with an acute-accented a (fa); the acute is a typesetting artifact of the held copy and this map uses fa."
|
|
24
|
+
note "Word division (particles wa/e/o, spacing after -te/-de forms), honorific hyphenation and capitalization in the document operate on morphological knowledge and are not encodable at the kana-character level; the worked constitution example of the document is therefore not pinned as a test."
|
|
25
|
+
}
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
tests {
|
|
29
|
+
"おかあさん" -> "okāsan"
|
|
30
|
+
"キーキー" -> "kīkī"
|
|
31
|
+
"くうかい" -> "kūkai"
|
|
32
|
+
"ケーキ" -> "kēki"
|
|
33
|
+
"とおり" -> "tōri"
|
|
34
|
+
"けいざい" -> "keizai"
|
|
35
|
+
"せいふ" -> "seifu"
|
|
36
|
+
"めいん" -> "mein"
|
|
37
|
+
"こうぞう" -> "kōzō"
|
|
38
|
+
"ばあい" -> "baai"
|
|
39
|
+
"かった" -> "katta"
|
|
40
|
+
"いっぽう" -> "ippō"
|
|
41
|
+
"ぶった" -> "butta"
|
|
42
|
+
"あっしゅく" -> "asshuku"
|
|
43
|
+
"あっちゃく" -> "atchaku"
|
|
44
|
+
"よっつ" -> "yottsu"
|
|
45
|
+
"しんかんせん" -> "shinkansen"
|
|
46
|
+
"ほんい" -> "hon’i"
|
|
47
|
+
"ほんやく" -> "hon’yaku"
|
|
48
|
+
"とんぼ" -> "tonbo"
|
|
49
|
+
"しんぱい" -> "shinpai"
|
|
50
|
+
"さんま" -> "sanma"
|
|
51
|
+
"とうきょう" -> "tōkyō"
|
|
52
|
+
"にゃっほー" -> "nyahhō"
|
|
53
|
+
"ヴァイオリン" -> "vaiorin"
|
|
54
|
+
"ウィキ" -> "wiki"
|
|
55
|
+
"チェック" -> "chekku"
|
|
56
|
+
"ジェ" -> "je"
|
|
57
|
+
"ヂェ" -> "je"
|
|
58
|
+
"スィ" -> "si"
|
|
59
|
+
"イェ" -> "ye"
|
|
60
|
+
"ティ" -> "ti"
|
|
61
|
+
"ディ" -> "di"
|
|
62
|
+
"トゥ" -> "tu"
|
|
63
|
+
"ドゥ" -> "du"
|
|
64
|
+
"ファフィフェフォ" -> "fafifefo"
|
|
65
|
+
"ヴュ" -> "vyu"
|
|
66
|
+
}
|
|
67
|
+
|
|
68
|
+
stage main {
|
|
69
|
+
|
|
70
|
+
# Syllabic n: apostrophe before a vowel or y (same word).
|
|
71
|
+
sub {
|
|
72
|
+
from capture(any("んン"))
|
|
73
|
+
to ref( 1 ) + "’"
|
|
74
|
+
after any("あいうえおやゆよアイウエオヤユヨヴ")
|
|
75
|
+
}
|
|
76
|
+
|
|
77
|
+
# CHARACTERS
|
|
78
|
+
parallel {
|
|
79
|
+
sub "あ" "a"
|
|
80
|
+
sub "い" "i"
|
|
81
|
+
sub "う" "u"
|
|
82
|
+
sub "え" "e"
|
|
83
|
+
sub "お" "o"
|
|
84
|
+
sub "おう" "ō"
|
|
85
|
+
sub "か" "ka"
|
|
86
|
+
sub "き" "ki"
|
|
87
|
+
sub "く" "ku"
|
|
88
|
+
sub "け" "ke"
|
|
89
|
+
sub "こ" "ko"
|
|
90
|
+
sub "きゃ" "kya"
|
|
91
|
+
sub "きゅ" "kyu"
|
|
92
|
+
sub "きょ" "kyo"
|
|
93
|
+
sub "きょう" "kyō"
|
|
94
|
+
sub "こう" "kō"
|
|
95
|
+
sub "が" "ga"
|
|
96
|
+
sub "ぎ" "gi"
|
|
97
|
+
sub "ぐ" "gu"
|
|
98
|
+
sub "げ" "ge"
|
|
99
|
+
sub "ご" "go"
|
|
100
|
+
sub "ぎゃ" "gya"
|
|
101
|
+
sub "ぎゅ" "gyu"
|
|
102
|
+
sub "ぎょ" "gyo"
|
|
103
|
+
sub "ぎょう" "gyō"
|
|
104
|
+
sub "ごう" "gō"
|
|
105
|
+
sub "さ" "sa"
|
|
106
|
+
sub "し" "shi"
|
|
107
|
+
sub "す" "su"
|
|
108
|
+
sub "せ" "se"
|
|
109
|
+
sub "そ" "so"
|
|
110
|
+
sub "しゃ" "sha"
|
|
111
|
+
sub "しゅ" "shu"
|
|
112
|
+
sub "しょ" "sho"
|
|
113
|
+
sub "しょう" "shō"
|
|
114
|
+
sub "そう" "sō"
|
|
115
|
+
sub "ざ" "za"
|
|
116
|
+
sub "じ" "ji"
|
|
117
|
+
sub "ず" "zu"
|
|
118
|
+
sub "ぜ" "ze"
|
|
119
|
+
sub "ぞ" "zo"
|
|
120
|
+
sub "じゃ" "ja"
|
|
121
|
+
sub "じゅ" "ju"
|
|
122
|
+
sub "じょ" "jo"
|
|
123
|
+
sub "じょう" "jō"
|
|
124
|
+
sub "ぞう" "zō"
|
|
125
|
+
sub "た" "ta"
|
|
126
|
+
sub "ち" "chi"
|
|
127
|
+
sub "つ" "tsu"
|
|
128
|
+
sub "て" "te"
|
|
129
|
+
sub "と" "to"
|
|
130
|
+
sub "ちゃ" "cha"
|
|
131
|
+
sub "ちゅ" "chu"
|
|
132
|
+
sub "ちょ" "cho"
|
|
133
|
+
sub "ちょう" "chō"
|
|
134
|
+
sub "とう" "tō"
|
|
135
|
+
sub "だ" "da"
|
|
136
|
+
sub "ぢ" "ji"
|
|
137
|
+
sub "づ" "zu"
|
|
138
|
+
sub "で" "de"
|
|
139
|
+
sub "ど" "do"
|
|
140
|
+
sub "ぢゃ" "ja"
|
|
141
|
+
sub "ぢゅ" "ju"
|
|
142
|
+
sub "ぢょ" "jo"
|
|
143
|
+
sub "どう" "dō"
|
|
144
|
+
sub "な" "na"
|
|
145
|
+
sub "に" "ni"
|
|
146
|
+
sub "ぬ" "nu"
|
|
147
|
+
sub "ね" "ne"
|
|
148
|
+
sub "の" "no"
|
|
149
|
+
sub "にゃ" "nya"
|
|
150
|
+
sub "にゅ" "nyu"
|
|
151
|
+
sub "にょ" "nyo"
|
|
152
|
+
sub "にょう" "nyō"
|
|
153
|
+
sub "のう" "nō"
|
|
154
|
+
sub "は" "ha"
|
|
155
|
+
sub "ひ" "hi"
|
|
156
|
+
sub "ふ" "fu"
|
|
157
|
+
sub "へ" "he"
|
|
158
|
+
sub "ほ" "ho"
|
|
159
|
+
sub "ひゃ" "hya"
|
|
160
|
+
sub "ひゅ" "hyu"
|
|
161
|
+
sub "ひょ" "hyo"
|
|
162
|
+
sub "ひょう" "hyō"
|
|
163
|
+
sub "ほう" "hō"
|
|
164
|
+
sub "ば" "ba"
|
|
165
|
+
sub "び" "bi"
|
|
166
|
+
sub "ぶ" "bu"
|
|
167
|
+
sub "べ" "be"
|
|
168
|
+
sub "ぼ" "bo"
|
|
169
|
+
sub "びゃ" "bya"
|
|
170
|
+
sub "びゅ" "byu"
|
|
171
|
+
sub "びょ" "byo"
|
|
172
|
+
sub "びょう" "byō"
|
|
173
|
+
sub "ぼう" "bō"
|
|
174
|
+
sub "ぱ" "pa"
|
|
175
|
+
sub "ぴ" "pi"
|
|
176
|
+
sub "ぷ" "pu"
|
|
177
|
+
sub "ぺ" "pe"
|
|
178
|
+
sub "ぽ" "po"
|
|
179
|
+
sub "ぴゃ" "pya"
|
|
180
|
+
sub "ぴゅ" "pyu"
|
|
181
|
+
sub "ぴょ" "pyo"
|
|
182
|
+
sub "ぴょう" "pyō"
|
|
183
|
+
sub "ぽう" "pō"
|
|
184
|
+
sub "ま" "ma"
|
|
185
|
+
sub "み" "mi"
|
|
186
|
+
sub "む" "mu"
|
|
187
|
+
sub "め" "me"
|
|
188
|
+
sub "も" "mo"
|
|
189
|
+
sub "みゃ" "mya"
|
|
190
|
+
sub "みゅ" "myu"
|
|
191
|
+
sub "みょ" "myo"
|
|
192
|
+
sub "みょう" "myō"
|
|
193
|
+
sub "もう" "mō"
|
|
194
|
+
sub "や" "ya"
|
|
195
|
+
sub "ゆ" "yu"
|
|
196
|
+
sub "よ" "yo"
|
|
197
|
+
sub "よう" "yō"
|
|
198
|
+
sub "ら" "ra"
|
|
199
|
+
sub "り" "ri"
|
|
200
|
+
sub "る" "ru"
|
|
201
|
+
sub "れ" "re"
|
|
202
|
+
sub "ろ" "ro"
|
|
203
|
+
sub "りゃ" "rya"
|
|
204
|
+
sub "りゅ" "ryu"
|
|
205
|
+
sub "りょ" "ryo"
|
|
206
|
+
sub "りょう" "ryō"
|
|
207
|
+
sub "ろう" "rō"
|
|
208
|
+
sub "わ" "wa"
|
|
209
|
+
sub "を" "o"
|
|
210
|
+
sub "ん" "n"
|
|
211
|
+
|
|
212
|
+
# Foreign-sound extensions (document table, katakana forms)
|
|
213
|
+
sub "イェ" "ye"
|
|
214
|
+
sub "ウィ" "wi"
|
|
215
|
+
sub "ウェ" "we"
|
|
216
|
+
sub "ウォ" "wo"
|
|
217
|
+
sub "ヴァ" "va"
|
|
218
|
+
sub "ヴィ" "vi"
|
|
219
|
+
sub "ヴ" "vu"
|
|
220
|
+
sub "ヴェ" "ve"
|
|
221
|
+
sub "ヴォ" "vo"
|
|
222
|
+
sub "ヴュ" "vyu"
|
|
223
|
+
sub "スィ" "si"
|
|
224
|
+
sub "ジェ" "je"
|
|
225
|
+
sub "ヂェ" "je"
|
|
226
|
+
sub "チェ" "che"
|
|
227
|
+
sub "ティ" "ti"
|
|
228
|
+
sub "ディ" "di"
|
|
229
|
+
sub "トゥ" "tu"
|
|
230
|
+
sub "ドゥ" "du"
|
|
231
|
+
sub "ファ" "fa"
|
|
232
|
+
sub "フィ" "fi"
|
|
233
|
+
sub "フェ" "fe"
|
|
234
|
+
sub "フォ" "fo"
|
|
235
|
+
|
|
236
|
+
# Katakana
|
|
237
|
+
sub "ア" "a"
|
|
238
|
+
sub "イ" "i"
|
|
239
|
+
sub "ウ" "u"
|
|
240
|
+
sub "エ" "e"
|
|
241
|
+
sub "オ" "o"
|
|
242
|
+
sub "オウ" "ō"
|
|
243
|
+
sub "カ" "ka"
|
|
244
|
+
sub "キ" "ki"
|
|
245
|
+
sub "ク" "ku"
|
|
246
|
+
sub "ケ" "ke"
|
|
247
|
+
sub "コ" "ko"
|
|
248
|
+
sub "キャ" "kya"
|
|
249
|
+
sub "キュ" "kyu"
|
|
250
|
+
sub "キョ" "kyo"
|
|
251
|
+
sub "キョウ" "kyō"
|
|
252
|
+
sub "コウ" "kō"
|
|
253
|
+
sub "ガ" "ga"
|
|
254
|
+
sub "ギ" "gi"
|
|
255
|
+
sub "グ" "gu"
|
|
256
|
+
sub "ゲ" "ge"
|
|
257
|
+
sub "ゴ" "go"
|
|
258
|
+
sub "ギャ" "gya"
|
|
259
|
+
sub "ギュ" "gyu"
|
|
260
|
+
sub "ギョ" "gyo"
|
|
261
|
+
sub "ギョウ" "gyō"
|
|
262
|
+
sub "ゴウ" "gō"
|
|
263
|
+
sub "サ" "sa"
|
|
264
|
+
sub "シ" "shi"
|
|
265
|
+
sub "ス" "su"
|
|
266
|
+
sub "セ" "se"
|
|
267
|
+
sub "ソ" "so"
|
|
268
|
+
sub "シャ" "sha"
|
|
269
|
+
sub "シュ" "shu"
|
|
270
|
+
sub "ショ" "sho"
|
|
271
|
+
sub "ショウ" "shō"
|
|
272
|
+
sub "ソウ" "sō"
|
|
273
|
+
sub "ザ" "za"
|
|
274
|
+
sub "ジ" "ji"
|
|
275
|
+
sub "ズ" "zu"
|
|
276
|
+
sub "ゼ" "ze"
|
|
277
|
+
sub "ゾ" "zo"
|
|
278
|
+
sub "ジャ" "ja"
|
|
279
|
+
sub "ジュ" "ju"
|
|
280
|
+
sub "ジョ" "jo"
|
|
281
|
+
sub "ジョウ" "jō"
|
|
282
|
+
sub "ゾウ" "zō"
|
|
283
|
+
sub "タ" "ta"
|
|
284
|
+
sub "チ" "chi"
|
|
285
|
+
sub "ツ" "tsu"
|
|
286
|
+
sub "テ" "te"
|
|
287
|
+
sub "ト" "to"
|
|
288
|
+
sub "チャ" "cha"
|
|
289
|
+
sub "チュ" "chu"
|
|
290
|
+
sub "チョ" "cho"
|
|
291
|
+
sub "チョウ" "chō"
|
|
292
|
+
sub "トウ" "tō"
|
|
293
|
+
sub "ダ" "da"
|
|
294
|
+
sub "ヂ" "ji"
|
|
295
|
+
sub "ヅ" "zu"
|
|
296
|
+
sub "デ" "de"
|
|
297
|
+
sub "ド" "do"
|
|
298
|
+
sub "ヂャ" "ja"
|
|
299
|
+
sub "ヂュ" "ju"
|
|
300
|
+
sub "ヂョ" "jo"
|
|
301
|
+
sub "ドウ" "dō"
|
|
302
|
+
sub "ナ" "na"
|
|
303
|
+
sub "ニ" "ni"
|
|
304
|
+
sub "ヌ" "nu"
|
|
305
|
+
sub "ネ" "ne"
|
|
306
|
+
sub "ノ" "no"
|
|
307
|
+
sub "ニャ" "nya"
|
|
308
|
+
sub "ニュ" "nyu"
|
|
309
|
+
sub "ニョ" "nyo"
|
|
310
|
+
sub "ニョウ" "nyō"
|
|
311
|
+
sub "ノウ" "nō"
|
|
312
|
+
sub "ハ" "ha"
|
|
313
|
+
sub "ヒ" "hi"
|
|
314
|
+
sub "フ" "fu"
|
|
315
|
+
sub "ヘ" "he"
|
|
316
|
+
sub "ホ" "ho"
|
|
317
|
+
sub "ヒャ" "hya"
|
|
318
|
+
sub "ヒュ" "hyu"
|
|
319
|
+
sub "ヒョ" "hyo"
|
|
320
|
+
sub "ヒョウ" "hyō"
|
|
321
|
+
sub "ホウ" "hō"
|
|
322
|
+
sub "バ" "ba"
|
|
323
|
+
sub "ビ" "bi"
|
|
324
|
+
sub "ブ" "bu"
|
|
325
|
+
sub "ベ" "be"
|
|
326
|
+
sub "ボ" "bo"
|
|
327
|
+
sub "ビャ" "bya"
|
|
328
|
+
sub "ビュ" "byu"
|
|
329
|
+
sub "ビョ" "byo"
|
|
330
|
+
sub "ビョウ" "byō"
|
|
331
|
+
sub "ボウ" "bō"
|
|
332
|
+
sub "パ" "pa"
|
|
333
|
+
sub "ピ" "pi"
|
|
334
|
+
sub "プ" "pu"
|
|
335
|
+
sub "ペ" "pe"
|
|
336
|
+
sub "ポ" "po"
|
|
337
|
+
sub "ピャ" "pya"
|
|
338
|
+
sub "ピュ" "pyu"
|
|
339
|
+
sub "ピョ" "pyo"
|
|
340
|
+
sub "ピョウ" "pyō"
|
|
341
|
+
sub "ポウ" "pō"
|
|
342
|
+
sub "マ" "ma"
|
|
343
|
+
sub "ミ" "mi"
|
|
344
|
+
sub "ム" "mu"
|
|
345
|
+
sub "メ" "me"
|
|
346
|
+
sub "モ" "mo"
|
|
347
|
+
sub "ミャ" "mya"
|
|
348
|
+
sub "ミュ" "myu"
|
|
349
|
+
sub "ミョ" "myo"
|
|
350
|
+
sub "ミョウ" "myō"
|
|
351
|
+
sub "モウ" "mō"
|
|
352
|
+
sub "ヤ" "ya"
|
|
353
|
+
sub "ユ" "yu"
|
|
354
|
+
sub "ヨ" "yo"
|
|
355
|
+
sub "ヨウ" "yō"
|
|
356
|
+
sub "ラ" "ra"
|
|
357
|
+
sub "リ" "ri"
|
|
358
|
+
sub "ル" "ru"
|
|
359
|
+
sub "レ" "re"
|
|
360
|
+
sub "ロ" "ro"
|
|
361
|
+
sub "リャ" "rya"
|
|
362
|
+
sub "リュ" "ryu"
|
|
363
|
+
sub "リョ" "ryo"
|
|
364
|
+
sub "リョウ" "ryō"
|
|
365
|
+
sub "ロウ" "rō"
|
|
366
|
+
sub "ワ" "wa"
|
|
367
|
+
sub "ヲ" "o"
|
|
368
|
+
sub "ン" "n"
|
|
369
|
+
}
|
|
370
|
+
|
|
371
|
+
# Long consonants (clause: long consonants). The small tsu doubles the
|
|
372
|
+
# following consonant letter; before ch the doubled letter is t
|
|
373
|
+
# (atchaku); before sh it doubles as s; before ts it doubles as t.
|
|
374
|
+
sub {
|
|
375
|
+
from any("っッ") + "ch"
|
|
376
|
+
to "tch"
|
|
377
|
+
}
|
|
378
|
+
sub {
|
|
379
|
+
from any("っッ") + capture(any("BbCcDdFfGgHhJjKkLlMmNnPpQqRrSsTtVvWwXxYyZz"))
|
|
380
|
+
to ref( 1 ) + ref( 1 )
|
|
381
|
+
}
|
|
382
|
+
sub {
|
|
383
|
+
from any("っッ")
|
|
384
|
+
to ""
|
|
385
|
+
}
|
|
386
|
+
|
|
387
|
+
# Long vowels: macron on doubled kana and on the lengthening bar.
|
|
388
|
+
# The document's repeat clause (baai, not bāi): a doubled kana vowel
|
|
389
|
+
# followed by another vowel letter is left as a sequence.
|
|
390
|
+
sub {
|
|
391
|
+
from "a" + any("ーa")
|
|
392
|
+
to "ā"
|
|
393
|
+
not_after any("あいうえおAIUEOaiueoー")
|
|
394
|
+
}
|
|
395
|
+
sub {
|
|
396
|
+
from "i" + any("ーi")
|
|
397
|
+
to "ī"
|
|
398
|
+
not_after any("あいうえおAIUEOaiueoー")
|
|
399
|
+
}
|
|
400
|
+
sub {
|
|
401
|
+
from "u" + any("ーu")
|
|
402
|
+
to "ū"
|
|
403
|
+
not_after any("あいうえおAIUEOaiueoー")
|
|
404
|
+
}
|
|
405
|
+
sub {
|
|
406
|
+
from "e" + any("ーe")
|
|
407
|
+
to "ē"
|
|
408
|
+
not_after any("あいうえおAIUEOaiueoー")
|
|
409
|
+
}
|
|
410
|
+
sub {
|
|
411
|
+
from "o" + any("ーo")
|
|
412
|
+
to "ō"
|
|
413
|
+
not_after any("あいうえおAIUEOaiueoー")
|
|
414
|
+
}
|
|
415
|
+
|
|
416
|
+
}
|
|
417
|
+
}
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: interscript-maps
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 3.
|
|
4
|
+
version: 3.3.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ribose Inc.
|
|
@@ -229,7 +229,7 @@ files:
|
|
|
229
229
|
- maps/bsi-kor-Kore-Latn-6505-1982.isc
|
|
230
230
|
- maps/bsi-mkd-Cyrl-Latn-1958.isc
|
|
231
231
|
- maps/bsi-ron-Cyrl-Latn-1958.isc
|
|
232
|
-
- maps/bsi-rus-Cyrl-Latn-1958.isc
|
|
232
|
+
- maps/bsi-rus-Cyrl-Latn-2979-1958.isc
|
|
233
233
|
- maps/bsi-srp-Cyrl-Latn-1958.isc
|
|
234
234
|
- maps/bsi-ukr-Cyrl-Latn-1958.isc
|
|
235
235
|
- maps/by-bel-Cyrl-Latn-1998.isc
|
|
@@ -337,31 +337,52 @@ files:
|
|
|
337
337
|
- maps/iso-ara-Arab-Latn-233-2-1993.isc
|
|
338
338
|
- maps/iso-asm-Beng-Latn-15919-2001.isc
|
|
339
339
|
- maps/iso-ben-Beng-Latn-15919-2001.isc
|
|
340
|
+
- maps/iso-ben-Beng-Latn-15919-2026.isc
|
|
341
|
+
- maps/iso-doi-Takr-Latn-15919-2026.isc
|
|
340
342
|
- maps/iso-ell-Grek-Latn-843-1997-t1.isc
|
|
341
343
|
- maps/iso-ell-Grek-Latn-843-1997-t2.isc
|
|
342
344
|
- maps/iso-guj-Gujr-Latn-15919-2001.isc
|
|
345
|
+
- maps/iso-guj-Gujr-Latn-15919-2026.isc
|
|
346
|
+
- maps/iso-heb-Hebr-Latn-259-1984.isc
|
|
347
|
+
- maps/iso-heb-Hebr-Latn-259-2-1994.isc
|
|
343
348
|
- maps/iso-hin-Deva-Latn-15919-2001.isc
|
|
344
349
|
- maps/iso-inc-Deva-Latn-15919-2001.isc
|
|
350
|
+
- maps/iso-inc-Kthi-Latn-15919-2001.isc
|
|
351
|
+
- maps/iso-inc-Kthi-Latn-15919-2026.isc
|
|
345
352
|
- maps/iso-jpn-Hrkt-Latn-3602-1989.isc
|
|
346
353
|
- maps/iso-kan-Kana-Latn-15919-2001.isc
|
|
354
|
+
- maps/iso-kan-Kana-Latn-15919-2026.isc
|
|
355
|
+
- maps/iso-kas-Shrd-Latn-15919-2026.isc
|
|
347
356
|
- maps/iso-kat-Geor-Latn-9984-1996.isc
|
|
348
357
|
- maps/iso-kor-Hang-Latn-1996-method1.isc
|
|
349
358
|
- maps/iso-kor-Hang-Latn-1996-method2.isc
|
|
350
359
|
- maps/iso-mal-Mlym-Latn-15919-2001.isc
|
|
360
|
+
- maps/iso-mal-Mlym-Latn-15919-2026.isc
|
|
351
361
|
- maps/iso-mar-Deva-Latn-15919-2001.isc
|
|
362
|
+
- maps/iso-mar-Modi-Latn-15919-2026.isc
|
|
352
363
|
- maps/iso-nep-Deva-Latn-15919-2001.isc
|
|
364
|
+
- maps/iso-new-Newa-Latn-15919-2026.isc
|
|
353
365
|
- maps/iso-ori-Orya-Latn-15919-2001.isc
|
|
366
|
+
- maps/iso-ori-Orya-Latn-15919-2026.isc
|
|
354
367
|
- maps/iso-pan-Guru-Latn-15919-2001.isc
|
|
368
|
+
- maps/iso-pan-Guru-Latn-15919-2026.isc
|
|
355
369
|
- maps/iso-pli-Beng-Latn-15919-2001.isc
|
|
356
370
|
- maps/iso-pli-Deva-Latn-15919-2001.isc
|
|
357
371
|
- maps/iso-pli-Sinh-Latn-15919-2001.isc
|
|
358
372
|
- maps/iso-pli-Thai-Latn-15919-2001.isc
|
|
373
|
+
- maps/iso-pra-Brah-Latn-15919-2026.isc
|
|
359
374
|
- maps/iso-pra-Deva-Latn-15919-2001.isc
|
|
360
375
|
- maps/iso-prs-Arab-Latn-233-3-1999.isc
|
|
361
376
|
- maps/iso-rus-Cyrl-Latn-9-1995.isc
|
|
362
377
|
- maps/iso-san-Deva-Latn-15919-2001.isc
|
|
378
|
+
- maps/iso-san-Deva-Latn-15919-2026.isc
|
|
379
|
+
- maps/iso-san-Gran-Latn-15919-2026.isc
|
|
380
|
+
- maps/iso-sin-Sinh-Latn-15919-2001.isc
|
|
381
|
+
- maps/iso-sin-Sinh-Latn-15919-2026.isc
|
|
363
382
|
- maps/iso-tam-Taml-Latn-15919-2001.isc
|
|
383
|
+
- maps/iso-tam-Taml-Latn-15919-2026.isc
|
|
364
384
|
- maps/iso-tel-Telu-Latn-15919-2001.isc
|
|
385
|
+
- maps/iso-tel-Telu-Latn-15919-2026.isc
|
|
365
386
|
- maps/iso-tha-Thai-Latn-11940-1998.isc
|
|
366
387
|
- maps/kp-kor-Hang-Latn-2002.isc
|
|
367
388
|
- maps/lshk-yue-Hani-Latn-jyutping-1993.isc
|
|
@@ -454,6 +475,7 @@ files:
|
|
|
454
475
|
- maps/var-hin-Deva-Latn-hunterian-1872.isc
|
|
455
476
|
- maps/var-jpn-Hrkt-Latn-hepburn-1886.isc
|
|
456
477
|
- maps/var-jpn-Hrkt-Latn-hepburn-1954.isc
|
|
478
|
+
- maps/var-jpn-Hrkt-Latn-komaba-2009.isc
|
|
457
479
|
- maps/var-kor-Hang-Hang-jamo.isc
|
|
458
480
|
- maps/var-kor-Hang-Latn-mr-1939.isc
|
|
459
481
|
- maps/var-kor-Kore-Hang-2013.isc
|
|
@@ -1,199 +0,0 @@
|
|
|
1
|
-
system "BSI:rus-Cyrl:Latn:1958" {
|
|
2
|
-
|
|
3
|
-
metadata {
|
|
4
|
-
authority_id bsi
|
|
5
|
-
id 1958
|
|
6
|
-
language iso-639-2:rus
|
|
7
|
-
source_script Cyrl
|
|
8
|
-
destination_script Latn
|
|
9
|
-
name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Russian column (the British system)"
|
|
10
|
-
url https://www.bsigroup.com
|
|
11
|
-
creation_date 1958
|
|
12
|
-
confirmation_date 2000-05
|
|
13
|
-
description { BS 2979:1958, Table A, Russian column: the "British" system for (modern) Cyrillic.
|
|
14
|
-
Table A is a five-column family table (East Slavonic: Russian, Ukrainian,
|
|
15
|
-
Byelorussian; South Slavonic: Bulgarian, Serbian and Macedonian); this map is the
|
|
16
|
-
Russian column. The Serbian and Macedonian column gives the latinica, the existing
|
|
17
|
-
Latin alphabet of Serbo-Croat. British Standard confirmed December 1998; the BSI
|
|
18
|
-
05-2000 reprint is the digitized edition.
|
|
19
|
-
}
|
|
20
|
-
|
|
21
|
-
notes {
|
|
22
|
-
note "NOTE 1. For extreme simplicity, when avoidance of ambiguity in back transliteration is not a paramount consideration, all accents, diacritics, etc., may be omitted in the English rendering; the document's own examples apply this (e.g. the example rendering of Khozyaistvo shows й without the breve). This map applies the table as printed, with the diacritics."
|
|
23
|
-
note "NOTE 2. Cyrillic characters for which the transliteration is given in parentheses (і, ѣ), though no longer in official use, are sometimes found in the literature, e.g. in emigre or the older literature. This map renders them as given in the parentheses."
|
|
24
|
-
note "NOTE 4. For transliteration of Moldavian, see Table C in Section 2 (ISO/R9)."
|
|
25
|
-
note "Rows 45 (the little yus), 46 (fita) and 47 (izhitsa) carry parenthesized obsolete romanizations whose exact diacritics the scan does not resolve unambiguously; this map does not render those three characters rather than guess them."
|
|
26
|
-
note "Row 38: the table gives the choice of right double quotation mark or straight double quotation mark for ъ; this map renders the right double quotation mark (U+201D). Row 40 likewise offers two apostrophe forms for ь; this map renders the right single quotation mark (U+2019)."
|
|
27
|
-
note "Row 28+27: the character sequence тс is romanized t-s with a hyphen, distinguishing it from ц, romanized ts. Footnote to Table A: final ъ, now obsolete in Russian, is disregarded when encountered (this map deletes it, per the row 38 rendering choice above)."
|
|
28
|
-
note "Other columns of Table A (Ukrainian, Byelorussian, Bulgarian, Serbian and Macedonian) are separate maps."
|
|
29
|
-
}
|
|
30
|
-
}
|
|
31
|
-
|
|
32
|
-
tests {
|
|
33
|
-
# document examples (Russian items, British column)
|
|
34
|
-
"Бюллетень" -> "Byulleten’"
|
|
35
|
-
"Известия" -> "Izvestiya"
|
|
36
|
-
"Академии Наук" -> "Akademii Nauk"
|
|
37
|
-
"Ленинград" -> "Leningrad"
|
|
38
|
-
# the document's example prints Promyshlennost' (NOTE 1 permits dropping diacritics);
|
|
39
|
-
# the table specifies ȳ for ы and this map follows the table
|
|
40
|
-
"Техника Промышленность и Торговля" -> "Tekhnika Promȳshlennost’ i Torgovlya"
|
|
41
|
-
"Москва" -> "Moskva"
|
|
42
|
-
# table rows, upper and lower
|
|
43
|
-
"А" -> "A"
|
|
44
|
-
"а" -> "a"
|
|
45
|
-
"Б" -> "B"
|
|
46
|
-
"б" -> "b"
|
|
47
|
-
"В" -> "V"
|
|
48
|
-
"в" -> "v"
|
|
49
|
-
"Г" -> "G"
|
|
50
|
-
"г" -> "g"
|
|
51
|
-
"Д" -> "D"
|
|
52
|
-
"д" -> "d"
|
|
53
|
-
"Е" -> "E"
|
|
54
|
-
"е" -> "e"
|
|
55
|
-
"Ё" -> "Ě"
|
|
56
|
-
"ё" -> "ě"
|
|
57
|
-
"Ж" -> "Zh"
|
|
58
|
-
"ж" -> "zh"
|
|
59
|
-
"З" -> "Z"
|
|
60
|
-
"з" -> "z"
|
|
61
|
-
"И" -> "I"
|
|
62
|
-
"и" -> "i"
|
|
63
|
-
"Й" -> "Ĭ"
|
|
64
|
-
"й" -> "ĭ"
|
|
65
|
-
"К" -> "K"
|
|
66
|
-
"к" -> "k"
|
|
67
|
-
"Л" -> "L"
|
|
68
|
-
"л" -> "l"
|
|
69
|
-
"М" -> "M"
|
|
70
|
-
"м" -> "m"
|
|
71
|
-
"Н" -> "N"
|
|
72
|
-
"н" -> "n"
|
|
73
|
-
"О" -> "O"
|
|
74
|
-
"о" -> "o"
|
|
75
|
-
"П" -> "P"
|
|
76
|
-
"п" -> "p"
|
|
77
|
-
"Р" -> "R"
|
|
78
|
-
"р" -> "r"
|
|
79
|
-
"С" -> "S"
|
|
80
|
-
"с" -> "s"
|
|
81
|
-
"Т" -> "T"
|
|
82
|
-
"т" -> "t"
|
|
83
|
-
"Тс" -> "T-s"
|
|
84
|
-
"тс" -> "t-s"
|
|
85
|
-
"У" -> "U"
|
|
86
|
-
"у" -> "u"
|
|
87
|
-
"Ф" -> "F"
|
|
88
|
-
"ф" -> "f"
|
|
89
|
-
"Х" -> "Kh"
|
|
90
|
-
"х" -> "kh"
|
|
91
|
-
"Ц" -> "Ts"
|
|
92
|
-
"ц" -> "ts"
|
|
93
|
-
"Ч" -> "Ch"
|
|
94
|
-
"ч" -> "ch"
|
|
95
|
-
"Ш" -> "Sh"
|
|
96
|
-
"ш" -> "sh"
|
|
97
|
-
"Щ" -> "Shch"
|
|
98
|
-
"щ" -> "shch"
|
|
99
|
-
"Ъ" -> "”"
|
|
100
|
-
"ъ" -> "”"
|
|
101
|
-
"Ы" -> "Ȳ"
|
|
102
|
-
"ы" -> "ȳ"
|
|
103
|
-
"Ь" -> "’"
|
|
104
|
-
"ь" -> "’"
|
|
105
|
-
"Э" -> "É"
|
|
106
|
-
"э" -> "é"
|
|
107
|
-
"Ю" -> "Yu"
|
|
108
|
-
"ю" -> "yu"
|
|
109
|
-
"Я" -> "Ya"
|
|
110
|
-
"я" -> "ya"
|
|
111
|
-
"І" -> "I"
|
|
112
|
-
"і" -> "i"
|
|
113
|
-
"Ѣ" -> "Ě"
|
|
114
|
-
"ѣ" -> "ě"
|
|
115
|
-
}
|
|
116
|
-
|
|
117
|
-
stage main {
|
|
118
|
-
|
|
119
|
-
# CHARACTERS
|
|
120
|
-
parallel {
|
|
121
|
-
sub "Тс" "T-s"
|
|
122
|
-
sub "тс" "t-s"
|
|
123
|
-
sub "Щ" "Shch"
|
|
124
|
-
sub "Ё" "Ě"
|
|
125
|
-
sub "Ж" "Zh"
|
|
126
|
-
sub "Й" "Ĭ"
|
|
127
|
-
sub "Х" "Kh"
|
|
128
|
-
sub "Ц" "Ts"
|
|
129
|
-
sub "Ч" "Ch"
|
|
130
|
-
sub "Ш" "Sh"
|
|
131
|
-
sub "Ы" "Ȳ"
|
|
132
|
-
sub "Э" "É"
|
|
133
|
-
sub "Ю" "Yu"
|
|
134
|
-
sub "Я" "Ya"
|
|
135
|
-
sub "Ѣ" "Ě"
|
|
136
|
-
sub "Ъ" "”"
|
|
137
|
-
sub "Ь" "’"
|
|
138
|
-
sub "А" "A"
|
|
139
|
-
sub "Б" "B"
|
|
140
|
-
sub "В" "V"
|
|
141
|
-
sub "Г" "G"
|
|
142
|
-
sub "Д" "D"
|
|
143
|
-
sub "Е" "E"
|
|
144
|
-
sub "З" "Z"
|
|
145
|
-
sub "И" "I"
|
|
146
|
-
sub "І" "I"
|
|
147
|
-
sub "К" "K"
|
|
148
|
-
sub "Л" "L"
|
|
149
|
-
sub "М" "M"
|
|
150
|
-
sub "Н" "N"
|
|
151
|
-
sub "О" "O"
|
|
152
|
-
sub "П" "P"
|
|
153
|
-
sub "Р" "R"
|
|
154
|
-
sub "С" "S"
|
|
155
|
-
sub "Т" "T"
|
|
156
|
-
sub "У" "U"
|
|
157
|
-
sub "Ф" "F"
|
|
158
|
-
|
|
159
|
-
sub "щ" "shch"
|
|
160
|
-
sub "тс" "t-s"
|
|
161
|
-
sub "ё" "ě"
|
|
162
|
-
sub "ж" "zh"
|
|
163
|
-
sub "й" "ĭ"
|
|
164
|
-
sub "х" "kh"
|
|
165
|
-
sub "ц" "ts"
|
|
166
|
-
sub "ч" "ch"
|
|
167
|
-
sub "ш" "sh"
|
|
168
|
-
sub "ы" "ȳ"
|
|
169
|
-
sub "э" "é"
|
|
170
|
-
sub "ю" "yu"
|
|
171
|
-
sub "я" "ya"
|
|
172
|
-
sub "ѣ" "ě"
|
|
173
|
-
sub "ъ" "”"
|
|
174
|
-
sub "ь" "’"
|
|
175
|
-
sub "а" "a"
|
|
176
|
-
sub "б" "b"
|
|
177
|
-
sub "в" "v"
|
|
178
|
-
sub "г" "g"
|
|
179
|
-
sub "д" "d"
|
|
180
|
-
sub "е" "e"
|
|
181
|
-
sub "з" "z"
|
|
182
|
-
sub "и" "i"
|
|
183
|
-
sub "і" "i"
|
|
184
|
-
sub "к" "k"
|
|
185
|
-
sub "л" "l"
|
|
186
|
-
sub "м" "m"
|
|
187
|
-
sub "н" "n"
|
|
188
|
-
sub "о" "o"
|
|
189
|
-
sub "п" "p"
|
|
190
|
-
sub "р" "r"
|
|
191
|
-
sub "с" "s"
|
|
192
|
-
sub "т" "t"
|
|
193
|
-
sub "у" "u"
|
|
194
|
-
sub "ф" "f"
|
|
195
|
-
}
|
|
196
|
-
|
|
197
|
-
}
|
|
198
|
-
|
|
199
|
-
}
|