interscript 0.1.3 → 0.1.4

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 643981da933194b2464ea279e9d31b9fcd9d32519c5cd236ed805855c93755ad
4
- data.tar.gz: f54c4303bb02f0a873cfdf96287d78321648cee19c685bf338cb9f8e2f642c56
3
+ metadata.gz: 6228d56d873603190ed290757f3e8056258cb88761b93405e15f06d25a08cba5
4
+ data.tar.gz: 0ceb25cb5862530d2c4798f921c4eaa5e9d999844266e8eab1d6bcd3d4b96842
5
5
  SHA512:
6
- metadata.gz: 2d8cfd0d60e2d41d8b1e31b4e61353b0bc7fd5ac4fc426d4304ccc86bc0bb6d84b4b4a2a6e44bb342afa6c20202a4bca4180a1f5037c73072e246038c6f36f1f
7
- data.tar.gz: 2a5fffac1de98702494f69d55b2de5200684195b0f7948619bfa2ae9f3f97810c731868f2550578f5ad97a9db9fa72d9c2abad24451437b7e08673dfc1cd97d8
6
+ metadata.gz: 301342d3cc50849fcb7f14c2b8b42404929cef1ed47192bc9cda236333b7b147c55d7b98648becc9c84d1b8790e6dbeffa30ecb27f472adf803463416e9babdc
7
+ data.tar.gz: cf95797a136ff95dfd3edc66378c0b6320f6a87325206d56c5e9acda381733b4168d8f651cb15a30c8a5b40add43bd3b2eeafde24bc19a959de0eb6983ad8359
@@ -1,3 +1,3 @@
1
1
  module Interscript
2
- VERSION = "0.1.3"
2
+ VERSION = "0.1.4"
3
3
  end
@@ -0,0 +1,141 @@
1
+ ---
2
+ authority_id: alalc
3
+ id: 1997
4
+ language: aze
5
+ source_script: Cyrl
6
+ destination_script: Latn
7
+ name: ALA-LC Romanization Table -- Azerbaijani (1997)
8
+ url: https://transliteration.eki.ee/pdf/Azerbaijani.pdf
9
+ creation_date: 1997
10
+ description: |
11
+ ALA-LC Romanization Tables: Transliteration Schemes for Non-Roman Scripts. Randal K. Berry (ed.). Library of Congress, 1997.
12
+
13
+ notes:
14
+ - "Ј ј replaced Й й in 1959 (Roman: y; ISO 9: j; ALA-LC: ĭ)."
15
+
16
+ tests: # from internet
17
+ - source: Азәрбајҹан дили
18
+ expected: Azărbaı̐jan dili
19
+ - source: |
20
+ Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад вә бәрабәр доғулурлар.
21
+ Онларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар.
22
+ expected: |
23
+ Bu̇tu̇n insanlar lăı̐agăt vă ḣu̇guglaryna ġȯră azad vă bărabăr doghulurlar.
24
+ Onlaryn shu̇urlary vă vijdanlary var vă bir-birlărină mu̇nasibătdă gardashlyg ruḣunda davranmalydyrlar.
25
+ - source: |
26
+ Азәрбајҹан! Азәрбајҹан!
27
+ Еј гәһрәман өвладын шанлы Вәтәни!
28
+ Сәндән өтрү ҹан вермәјә ҹүмлә һазырыз!
29
+ Сәндән өтрү ган төкмәјә ҹүмлә гадириз!
30
+ Үчрәнҝли бајрағынла мәсуд јаша!
31
+ Үчрәнҝли бајрағынла мәсуд јаша!
32
+ Минләрлә ҹан гурбан олду,
33
+ Синән һәрбә мејдан олду!
34
+ Һүгугундан кечән әсҝәр,
35
+ Һәрә бир гәһрәман олду!
36
+ Сән оласан ҝүлүстан,
37
+ Сәнә һәр ан ҹан гурбан!
38
+ Сәнә мин бир мәһәббәт
39
+ Синәмдә тутмуш мәкан!
40
+ Намусуну һифз етмәјә,
41
+ Бајрағыны јүксәлтмәјә
42
+ Намусуну һифз етмәјә,
43
+ Ҹүмлә ҝәнҹләр мүштагдыр!
44
+ Шанлы Вәтән! Шанлы Вәтән!
45
+ Азәрбајҹан! Азәрбајҹан!
46
+ Азәрбајҹан! Азәрбајҹан!
47
+ expected: |
48
+ Azărbaı̐jan! Azărbaı̐jan!
49
+ Eı̐ găḣrăman ȯvladyn shanly Vătăni!
50
+ Săndăn ȯtru̇ jan vermăı̐ă ju̇mlă ḣazyryz!
51
+ Săndăn ȯtru̇ gan tȯkmăı̐ă ju̇mlă gadiriz!
52
+ U̇chrănġli baı̐raghynla măsud ı̐asha!
53
+ U̇chrănġli baı̐raghynla măsud ı̐asha!
54
+ Minlărlă jan gurban oldu,
55
+ Sinăn ḣărbă meı̐dan oldu!
56
+ Ḣu̇gugundan kechăn ăsġăr,
57
+ Ḣără bir găḣrăman oldu!
58
+ Săn olasan ġu̇lu̇stan,
59
+ Sănă ḣăr an jan gurban!
60
+ Sănă min bir măḣăbbăt
61
+ Sinămdă tutmush măkan!
62
+ Namusunu ḣifz etmăı̐ă,
63
+ Baı̐raghyny ı̐u̇ksăltmăı̐ă
64
+ Namusunu ḣifz etmăı̐ă,
65
+ Ju̇mlă ġănjlăr mu̇shtagdyr!
66
+ Shanly Vătăn! Shanly Vătăn!
67
+ Azărbaı̐jan! Azărbaı̐jan!
68
+ Azărbaı̐jan! Azărbaı̐jan!
69
+
70
+ map:
71
+ characters:
72
+ '\u0410': 'A' # А
73
+ '\u0411': 'B' # Б
74
+ '\u0412': 'V' # В
75
+ '\u0413': 'G' # Г
76
+ '\u0492': 'Gh' # Ғ
77
+ '\u0414': 'D' # Д
78
+ '\u0415': 'E' # Е
79
+ '\u04D8': "A\u0306" # Ә
80
+ '\u0416': 'Zh' # Ж
81
+ '\u0417': 'Z' # З
82
+ '\u0418': 'I' # И
83
+ '\u042B': 'Y' # Ы
84
+ '\u0408': "I\u0310" # Ј
85
+ '\u0419': 'Y' # Й note[1]
86
+ '\u0419': 'Y' # Й
87
+ '\u041A': 'K' # К
88
+ '\u049C': "G\u0307" # Ҝ
89
+ '\u041B': 'L' # Л
90
+ '\u041C': 'M' # М
91
+ '\u041D': 'N' # Н
92
+ '\u041E': 'O' # О
93
+ '\u04E8': "O\u0307" # Ө
94
+ '\u041F': 'P' # П
95
+ '\u0420': 'R' # Р
96
+ '\u0421': 'S' # С
97
+ '\u0422': 'T' # Т
98
+ '\u0423': 'U' # У
99
+ '\u04AE': "U\u0307" # Ү
100
+ '\u0424': 'F' # Ф
101
+ '\u0425': 'Kh' # Х
102
+ '\u04BA': "H\u0307" # Һ
103
+ '\u0427': 'Ch' # Ч
104
+ '\u04B8': 'J' # Ҹ
105
+ '\u0428': 'Sh' # Ш
106
+
107
+ '\u0430': 'a' # а
108
+ '\u0431': 'b' # б
109
+ '\u0432': 'v' # в
110
+ '\u0433': 'g' # г
111
+ '\u0493': 'gh' # ғ
112
+ '\u0434': 'd' # д
113
+ '\u0435': 'e' # e
114
+ '\u04D9': "a\u0306" # ә
115
+ '\u0436': 'zh' # ж
116
+ '\u0437': 'z' # з
117
+ '\u0438': 'i' # и
118
+ '\u044B': 'y' # ы
119
+ '\u0458': "\u0131\u0310" # ј
120
+ '\u0439': 'y' # й note[1]
121
+ '\u043A': 'k' # к
122
+ '\u049D': "g\u0307" # ҝ
123
+ '\u043B': 'l' # л
124
+ '\u043C': 'm' # м
125
+ '\u043D': 'n' # н
126
+ '\u043E': 'o' # о
127
+ '\u04E9': "o\u0307" # ө
128
+ '\u043F': 'p' # п
129
+ '\u0440': 'r' # р
130
+ '\u0441': 's' # с
131
+ '\u0442': 't' # т
132
+ '\u0443': 'u' # у
133
+ '\u04AF': "u\u0307" # ү
134
+ '\u0444': 'f' # ф
135
+ '\u0445': 'kh' # х
136
+ '\u04BB': "h\u0307" # һ
137
+ '\u0447': 'ch' # ч
138
+ '\u04B9': 'j' # ҹ
139
+ '\u0448': 'sh' # ш
140
+
141
+ '\u2019': '\u2019'
@@ -0,0 +1,222 @@
1
+ ---
2
+ authority_id: alalc
3
+ id: 1997
4
+ language: rus
5
+ source_script: Cyrl
6
+ destination_script: Latn
7
+ name: ALA-LC Romanization System 1997
8
+ url: https://en.wikipedia.org/wiki/ALA-LC_romanization_for_Russian
9
+ creation_date: 1997
10
+ description: |
11
+ The ALA-LC Romanization tables for Slavic alphabets is a set of standards for romanization of texts
12
+ in various writing systems used in North American libraries and publications.
13
+ This version was published by the American Library Association and the Library of Congress in 1997.
14
+ This article is about the ALA-LC method of transliteration of Russian-language text from Cyrillic script to Latin script.
15
+
16
+ The formal, unambiguous version of the system requires some diacritics and two-letter tie characters which are often omitted in practice.
17
+
18
+ notes:
19
+ - Pre-1918 letters skipped
20
+ - Pre-18th century letters skipped
21
+
22
+ tests:
23
+ - source: Азов
24
+ expected: Azov
25
+ - source: Тамбов
26
+ expected: Tambov
27
+ - source: Барнаул
28
+ expected: Barnaul
29
+ - source: Кубань
30
+ expected: Kubanʹ
31
+ - source: Владимир
32
+ expected: Vladimir
33
+ - source: Ульяновск
34
+ expected: Ulʹi͡anovsk
35
+ - source: Грозный
36
+ expected: Groznyǐ
37
+ - source: Волгодонск
38
+ expected: Volgodonsk
39
+ - source: Дзержинский
40
+ expected: Dzerzhinskiǐ
41
+ - source: Нелидово
42
+ expected: Nelidovo
43
+ - source: Елизово
44
+ expected: Elizovo
45
+ - source: Чебоксары
46
+ expected: Cheboksary
47
+ - source: Ёлкин
48
+ expected: Ëlkin
49
+ - source: Озёрный
50
+ expected: Ozërnyǐ
51
+ - source: Жуков
52
+ expected: Zhukov
53
+ - source: Лужники
54
+ expected: Luzhniki
55
+ - source: Звенигород
56
+ expected: Zvenigorod
57
+ - source: Вязьма
58
+ expected: Vi͡azʹma
59
+ - source: Иркутск
60
+ expected: Irkutsk
61
+ - source: Апатиты
62
+ expected: Apatity
63
+ - source: Йошкар-Ола
64
+ expected: Ǐoshkar-Ola
65
+ - source: Бийск
66
+ expected: Biǐsk
67
+ - source: Киров
68
+ expected: Kirov
69
+ - source: Енисейск
70
+ expected: Eniseǐsk
71
+ - source: Ломоносов
72
+ expected: Lomonosov
73
+ - source: Нелидово
74
+ expected: Nelidovo
75
+ - source: Менделеев
76
+ expected: Mendeleev
77
+ - source: Каменка
78
+ expected: Kamenka
79
+ - source: Новосибирск
80
+ expected: Novosibirsk
81
+ - source: Кандалакша
82
+ expected: Kandalaksha
83
+ - source: Омск
84
+ expected: Omsk
85
+ - source: Красноярск
86
+ expected: Krasnoi͡arsk
87
+ - source: Петрозаводск
88
+ expected: Petrozavodsk
89
+ - source: Серпухов
90
+ expected: Serpukhov
91
+ - source: Ростов
92
+ expected: Rostov
93
+ - source: Северобайкальск
94
+ expected: Severobaǐkalʹsk
95
+ - source: Сковородино
96
+ expected: Skovorodino
97
+ - source: Чайковский
98
+ expected: Chaǐkovskiǐ
99
+ - source: Тамбов
100
+ expected: Tambov
101
+ - source: Мытищи
102
+ expected: Mytishchi
103
+ - source: Углич
104
+ expected: Uglich
105
+ - source: Дудинка
106
+ expected: Dudinka
107
+ - source: Фурманов
108
+ expected: Furmanov
109
+ - source: Уфа
110
+ expected: Ufa
111
+ - source: Хабаровск
112
+ expected: Khabarovsk
113
+ - source: Прохладный
114
+ expected: Prokhladnyǐ
115
+ - source: Цимлянск
116
+ expected: T͡Simli͡ansk
117
+ - source: Ельцин
118
+ expected: Elʹt͡sin
119
+ - source: Чебоксары
120
+ expected: Cheboksary
121
+ - source: Печора
122
+ expected: Pechora
123
+ - source: Шахтёрск
124
+ expected: Shakhtërsk
125
+ - source: Мышкин
126
+ expected: Myshkin
127
+ - source: Щёлково
128
+ expected: Shchëlkovo
129
+ - source: Ртищево
130
+ expected: Rtishchevo
131
+ - source: Подъездной
132
+ expected: Podʺezdnoǐ
133
+ - source: Ыттык-Кёль
134
+ expected: Yttyk-Këlʹ
135
+ - source: Тында
136
+ expected: Tynda
137
+ - source: Тюмень
138
+ expected: Ti͡umenʹ
139
+ - source: Электрогорск
140
+ expected: Ėlektrogorsk
141
+ - source: Радиоэлектроника
142
+ expected: Radioėlektronika
143
+ - source: Юбилейный
144
+ expected: I͡Ubileǐnyǐ
145
+ - source: Ключевская
146
+ expected: Kli͡uchevskai͡a
147
+ - source: Якутск
148
+ expected: I͡Akutsk
149
+ - source: Брянск
150
+ expected: Bri͡ansk
151
+
152
+ map:
153
+ characters:
154
+ "\u0027": "" # '
155
+ "\u0410": "A" # А
156
+ "\u0411": "B" # Б
157
+ "\u0412": "V" # В
158
+ "\u0413": "G" # Г
159
+ "\u0414": "D" # Д
160
+ "\u0415": "E" # Е
161
+ "\u0401": "Ë" # Ё
162
+ "\u0416": "Zh" # Ж
163
+ "\u0417": "Z" # З
164
+ "\u0418": "I" # И
165
+ "\u0419": "\u01CF" # Й
166
+ "\u041A": "K" # К
167
+ "\u041B": "L" # Л
168
+ "\u041C": "M" # М
169
+ "\u041D": "N" # Н
170
+ "\u041E": "O" # О
171
+ "\u041F": "P" # П
172
+ "\u0420": "R" # Р
173
+ "\u0421": "S" # С
174
+ "\u0422": "T" # Т
175
+ "\u0423": "U" # У
176
+ "\u0424": "F" # Ф
177
+ "\u0425": "Kh" # Х
178
+ "\u0426": "T\u0361S" # Ц
179
+ "\u0427": "Ch" # Ч
180
+ "\u0428": "Sh" # Ш
181
+ "\u0429": "Shch" # Щ
182
+ "\u042A": "ʺ" # Ъ
183
+ "\u042B": "Y" # Ы
184
+ "\u042C": "ʹ" # Ь
185
+ "\u042D": "E\u0307" # Э
186
+ "\u042E": "I\u0361U" # Ю
187
+ "\u042F": "I\u0361A" # Я
188
+
189
+ "\u0430": "a" # а
190
+ "\u0431": "b" # б
191
+ "\u0432": "v" # в
192
+ "\u0433": "g" # г
193
+ "\u0434": "d" # д
194
+ "\u0435": "e" # e
195
+ "\u0451": "ë" # ё
196
+ "\u0436": "zh" # ж
197
+ "\u0437": "z" # з
198
+ "\u0438": "i" # и
199
+ "\u0439": "\u01d0" # й
200
+ "\u043A": "k" # к
201
+ "\u043B": "l" # л
202
+ "\u043C": "m" # м
203
+ "\u043D": "n" # н
204
+ "\u043E": "o" # о
205
+ "\u043F": "p" # п
206
+ "\u0440": "r" # р
207
+ "\u0441": "s" # с
208
+ "\u0442": "t" # т
209
+ "\u0443": "u" # у
210
+ "\u0444": "f" # ф
211
+ "\u0445": "kh" # х
212
+ "\u0446": "t\u0361s" # ц
213
+ "\u0447": "ch" # ч
214
+ "\u0448": "sh" # ш
215
+ "\u0449": "shch" # щ
216
+ "\u044A": "ʺ" # ъ
217
+ "\u044B": "y" # ы
218
+ "\u044C": "ʹ" # ь
219
+ "\u044D": "e\u0307" # э
220
+ "\u044E": "i\u0361u" # ю
221
+ "\u044F": "i\u0361a" # я
222
+
@@ -0,0 +1,162 @@
1
+ ---
2
+ authority_id: alalc
3
+ id: 2012
4
+ language: rus
5
+ source_script: Cyrl
6
+ destination_script: Latn
7
+ name: ALA-LC Romanization System 2012
8
+ url: https://www.loc.gov/catdir/cpso/romanization/russian.pdf
9
+ creation_date: 2012
10
+ description: |
11
+ The ALA-LC Romanization tables for Slavic alphabets is a set of standards for romanization of texts
12
+ in various writing systems used in North American libraries and publications.
13
+ The latest version was published by the American Library Association and the Library of Congress in 2012.
14
+
15
+ notes:
16
+ - The letters І, Ѣ, Ѳ and Ѵ were eliminated in the orthographic reform of 1918. For other obsolete letters appearing in Russian texts, consult the Church Slavic table.
17
+
18
+ tests:
19
+ - source: Азов
20
+ expected: Azov
21
+ - source: Тамбов
22
+ expected: Tambov
23
+ - source: Барнаул
24
+ expected: Barnaul
25
+ - source: Кубань
26
+ expected: Kubanʹ
27
+ - source: Владимир
28
+ expected: Vladimir
29
+ - source: Ульяновск
30
+ expected: Ulʹi͡anovsk
31
+ - source: Грозный
32
+ expected: Groznyǐ
33
+ - source: Волгодонск
34
+ expected: Volgodonsk
35
+ - source: Дзержинский
36
+ expected: Dzerzhinskiǐ
37
+ - source: Нелидово
38
+ expected: Nelidovo
39
+ - source: Елизово
40
+ expected: Elizovo
41
+ - source: Чебоксары
42
+ expected: Cheboksary
43
+ - source: Ёлкин
44
+ expected: Ëlkin
45
+ - source: Озёрный
46
+ expected: Ozërnyǐ
47
+ - source: Жуков
48
+ expected: Zhukov
49
+ - source: Лужники
50
+ expected: Luzhniki
51
+ - source: Звенигород
52
+ expected: Zvenigorod
53
+ - source: Вязьма
54
+ expected: Vi͡azʹma
55
+ - source: Иркутск
56
+ expected: Irkutsk
57
+ - source: Апатиты
58
+ expected: Apatity
59
+ - source: Йошкар-Ола
60
+ expected: Ǐoshkar-Ola
61
+ - source: Бийск
62
+ expected: Biǐsk
63
+ - source: Киров
64
+ expected: Kirov
65
+ - source: Енисейск
66
+ expected: Eniseǐsk
67
+ - source: Ломоносов
68
+ expected: Lomonosov
69
+ - source: Нелидово
70
+ expected: Nelidovo
71
+ - source: Менделеев
72
+ expected: Mendeleev
73
+ - source: Каменка
74
+ expected: Kamenka
75
+ - source: Новосибирск
76
+ expected: Novosibirsk
77
+ - source: Кандалакша
78
+ expected: Kandalaksha
79
+ - source: Омск
80
+ expected: Omsk
81
+ - source: Красноярск
82
+ expected: Krasnoi͡arsk
83
+ - source: Петрозаводск
84
+ expected: Petrozavodsk
85
+ - source: Серпухов
86
+ expected: Serpukhov
87
+ - source: Ростов
88
+ expected: Rostov
89
+ - source: Северобайкальск
90
+ expected: Severobaǐkalʹsk
91
+ - source: Сковородино
92
+ expected: Skovorodino
93
+ - source: Чайковский
94
+ expected: Chaǐkovskiǐ
95
+ - source: Тамбов
96
+ expected: Tambov
97
+ - source: Мытищи
98
+ expected: Mytishchi
99
+ - source: Углич
100
+ expected: Uglich
101
+ - source: Дудинка
102
+ expected: Dudinka
103
+ - source: Фурманов
104
+ expected: Furmanov
105
+ - source: Уфа
106
+ expected: Ufa
107
+ - source: Хабаровск
108
+ expected: Khabarovsk
109
+ - source: Прохладный
110
+ expected: Prokhladnyǐ
111
+ - source: Цимлянск
112
+ expected: T͡Simli͡ansk
113
+ - source: Ельцин
114
+ expected: Elʹt͡sin
115
+ - source: Чебоксары
116
+ expected: Cheboksary
117
+ - source: Печора
118
+ expected: Pechora
119
+ - source: Шахтёрск
120
+ expected: Shakhtërsk
121
+ - source: Мышкин
122
+ expected: Myshkin
123
+ - source: Щёлково
124
+ expected: Shchëlkovo
125
+ - source: Ртищево
126
+ expected: Rtishchevo
127
+ - source: Подъездной
128
+ expected: Podʺezdnoǐ
129
+ - source: Ыттык-Кёль
130
+ expected: Yttyk-Këlʹ
131
+ - source: Тында
132
+ expected: Tynda
133
+ - source: Тюмень
134
+ expected: Ti͡umenʹ
135
+ - source: Электрогорск
136
+ expected: Ėlektrogorsk
137
+ - source: Радиоэлектроника
138
+ expected: Radioėlektronika
139
+ - source: Юбилейный
140
+ expected: I͡Ubileǐnyǐ
141
+ - source: Ключевская
142
+ expected: Kli͡uchevskai͡a
143
+ - source: Якутск
144
+ expected: I͡Akutsk
145
+ - source: Брянск
146
+ expected: Bri͡ansk
147
+
148
+ map:
149
+ inherit: alalc-rus-Cyrl-Latn-1997
150
+
151
+ characters:
152
+ '\u0406': "\u012A"
153
+ '\u0456': "\u012B"
154
+
155
+ '\u0462': "I\u0361E" # Ѣ
156
+ '\u0463': "i\u0361e" # ѣ
157
+
158
+ '\u0472': "F\u0307" # Ѳ
159
+ '\u0473': "f\u0307" # ѳ
160
+
161
+ '\u0474': "Y\u0307" # Ѵ
162
+ '\u0475': "y\u0307" # ѵ