interscript 0.1.2 → 0.1.7

data/maps/alalc-pli-Deva-Latn-2012.yaml

@@ -0,0 +1,144 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:pli
+source_script: Deva
+destination_script: Latn
+name: Pali Romanization, 2012
+url: https://www.loc.gov/catdir/cpso/romanization/pali.pdf
+creation_date: 2012
+description: |
+  ALA-LC Romanization table for Pali
+
+notes:
+
+  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+
+    a) when another vowel is indicated by its appropriate sign; and
+    b) when the absence of any vowel is indicated by the subscript sign ( ् ) called halanta or
+       virāma.
+
+  - |
+    Exception: Niggahīta combinations representing nasals are romanized by ṅ
+    before gutturals, ñ before palatals, ṇ before cerebrals, n before dentals, and m before
+    labials.
+
+tests:
+  - source: "तेन खो पन समयेन वेसालिया अविदूरे कलन्दगामो नाम अत्थि"
+    expected: "taena khao pana samayaena vaesaālaiyaā avaidaūrae kalanadagaāmao naāma atathai"
+  - source: "तत्थ सुदिन्‍नो नाम कलन्दपुत्तो सेट्ठिपुत्तो होति"
+    expected: "tatatha saudainanao naāma kalanadapautatao saeṭaṭhaipautatao haotai"
+  - source: "अथ खो सुदिन्‍नो कलन्दपुत्तो सम्बहुलेहि"
+    expected: "atha khao saudainanao kalanadapautatao samabahaulaehai"
+  - source: "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा"
+    expected: "tathaā cataurabhaiḥ paurauṣaḥ paraīkaṣayatae tayaāgaena śaīlaena gauṇaena karamaṇaā"
+  - source: "अथ खो सुदिन्‍नो कलन्दपुत्तो अचिरवुट्ठिताय परिसाय येन भगवा तेनुपसङ्कमि; उपसङ्कमित्वा भगवन्तं अभिवादेत्वा एकमन्तं निसीदि"
+    expected: "atha khao saudainanao kalanadapautatao acairavauṭaṭhaitaāya paraisaāya yaena bhagavaā taenaupasaṅakamai; upasaṅakamaitavaā bhagavanataṃ abhaivaādaetavaā ekamanataṃ naisaīdai"
+  - source: "अथ खो सुदिन्‍नस्स कलन्दपुत्तस्स मातापितरो सुदिन्‍नं कलन्दपुत्तं एतदवोचुं"
+    expected: "atha khao saudainanasasa kalanadapautatasasa maātaāpaitarao saudainanaṃ kalanadapautataṃ etadavaocauṃ"
+  - source: "त्वं खोसि, तात सुदिन्‍न, अम्हाकं एकपुत्तको पियो मनापो सुखेधितो सुखपरिहतो"
+    expected: "tavaṃ khaosai, taāta saudainana, amahaākaṃ ekapautatakao paiyao manaāpao saukhaedhaitao saukhaparaihatao"
+  - source: "न त्वं, तात सुदिन्‍न, किञ्‍चि दुक्खस्स जानासि"
+    expected: "na tavaṃ, taāta saudainana, kaiñacai daukakhasasa jaānaāsai"
+  - source: "अनुञ्‍ञातोम्हि किर मातापितूहि अगारस्मा अनगारियं पब्बज्‍जाया’’ति, हट्ठो उदग्गो पाणिना गत्तानि परिपुञ्छन्तो वुट्ठासि"
+    expected: "anauñañaātaomahai kaira maātaāpaitaūhai agaārasamaā anagaāraiyaṃ pababajajaāyaā’’tai, haṭaṭhao udagagao paāṇainaā gatataānai paraipauñachanatao vauṭaṭhaāsai"
+
+map:
+
+  rules:
+    # note[3]
+    - pattern: \u0902(?=[कखगघङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजझञ])
+      result: ñ
+    - pattern: \u0902(?=[टठडढण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ए': 'e'
+    'ओ': 'o'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'ka'
+    'ख': 'kha'
+    'ग': 'ga'
+    'घ': 'gha'
+    'ङ': 'ṅa'
+
+    # Palatals
+    'च': 'ca'
+    'छ': 'cha'
+    'ज': 'ja'
+    'झ': 'jha'
+    'ञ': 'ña'
+
+    # Cerebrals
+    'ट': 'ṭa'
+    'ठ': 'ṭha'
+    'ड': 'ḍa'
+    'ढ': 'ḍha'
+    'ण': 'ṇa'
+
+    # Dentals
+    'त': 'ta'
+    'थ': 'tha'
+    'द': 'da'
+    'ध': 'dha'
+    'न': 'na'
+
+    # Labials
+    'प': 'pa'
+    'फ': 'pha'
+    'ब': 'ba'
+    'भ': 'bha'
+    'म': 'ma'
+
+    # Semivowels
+    'य': 'ya'
+    'र': 'ra'
+    'ल': 'la'
+    'ळ': 'ḻa'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'ṣa'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+    # Visagga
+    'ः': 'ḥ'
+
+    # Niggahīta/Anusvāra
+    'ं': 'ṃ'
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'े': "e"
+    'ो': "o"
+    '्': ""
+    '‍': ''# Used for joining

data/maps/alalc-pra-Deva-Latn-2012.yaml

@@ -0,0 +1,47 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:pra
+source_script: Deva
+destination_script: Latn
+name: Prakrit Romanization, 2012
+url: https://www.loc.gov/catdir/cpso/romanization/sanskrit.pdf
+creation_date: 2012
+description: |
+  ALA-LC Romanization table for Prakrit
+
+notes:
+
+  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+
+    a) when another vowel is indicated by its appropriate sign; and
+    b) when the absence of any vowel is indicated by the subscript sign ( ् ) called halanta or
+       virāma.
+
+  - |
+    Exception: Anusvāra is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+    In other circumstances it is transliterated by a tilde (~) over the vowel.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "सृष्टिस्थितिविनाशानां शक्तिभूते सनातनि"
+    expected: "saṛṣaṭaisathaitaivainaāśaānaāṃ śakataibhaūtae sanaātanai"
+  - source: "गुणाश्रये गुणमये नारायणि नमोऽस्तु ते"
+    expected: "gauṇaāśarayae gauṇamayae naāraāyaṇai namao’satau tae"
+
+map:
+
+  inherit: "alalc-san-Deva-Latn-2012"

data/maps/alalc-rus-Cyrl-Latn-1997.yaml

@@ -0,0 +1,225 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:rus
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization System 1997
+alias:
+  ogc11122:
+    code: rus_Cyrl2Latn_ALA_1997
+    description: Russian ALA-Library of Congress 1997 System
+url: https://en.wikipedia.org/wiki/ALA-LC_romanization_for_Russian
+creation_date: 1997
+description: |
+  The ALA-LC Romanization tables for Slavic alphabets is a set of standards for romanization of texts
+  in various writing systems used in North American libraries and publications.
+  This version was published by the American Library Association and the Library of Congress in 1997.
+  This article is about the ALA-LC method of transliteration of Russian-language text from Cyrillic script to Latin script.
+
+  The formal, unambiguous version of the system requires some diacritics and two-letter tie characters which are often omitted in practice.
+
+notes:
+  - Pre-1918 letters skipped
+  - Pre-18th century letters skipped
+
+tests:
+  - source: Азов
+    expected: Azov
+  - source: Тамбов
+    expected: Tambov
+  - source: Барнаул
+    expected: Barnaul
+  - source: Кубань
+    expected: Kubanʹ
+  - source: Владимир
+    expected: Vladimir
+  - source: Ульяновск
+    expected: Ulʹi͡anovsk
+  - source: Грозный
+    expected: Groznyǐ
+  - source: Волгодонск
+    expected: Volgodonsk
+  - source: Дзержинский
+    expected: Dzerzhinskiǐ
+  - source: Нелидово
+    expected: Nelidovo
+  - source: Елизово
+    expected: Elizovo
+  - source: Чебоксары
+    expected: Cheboksary
+  - source: Ёлкин
+    expected: Ëlkin
+  - source: Озёрный
+    expected: Ozërnyǐ
+  - source: Жуков
+    expected: Zhukov
+  - source: Лужники
+    expected: Luzhniki
+  - source: Звенигород
+    expected: Zvenigorod
+  - source: Вязьма
+    expected: Vi͡azʹma
+  - source: Иркутск
+    expected: Irkutsk
+  - source: Апатиты
+    expected: Apatity
+  - source: Йошкар-Ола
+    expected: Ǐoshkar-Ola
+  - source: Бийск
+    expected: Biǐsk
+  - source: Киров
+    expected: Kirov
+  - source: Енисейск
+    expected: Eniseǐsk
+  - source: Ломоносов
+    expected: Lomonosov
+  - source: Нелидово
+    expected: Nelidovo
+  - source: Менделеев
+    expected: Mendeleev
+  - source: Каменка
+    expected: Kamenka
+  - source: Новосибирск
+    expected: Novosibirsk
+  - source: Кандалакша
+    expected: Kandalaksha
+  - source: Омск
+    expected: Omsk
+  - source: Красноярск
+    expected: Krasnoi͡arsk
+  - source: Петрозаводск
+    expected: Petrozavodsk
+  - source: Серпухов
+    expected: Serpukhov
+  - source: Ростов
+    expected: Rostov
+  - source: Северобайкальск
+    expected: Severobaǐkalʹsk
+  - source: Сковородино
+    expected: Skovorodino
+  - source: Чайковский
+    expected: Chaǐkovskiǐ
+  - source: Тамбов
+    expected: Tambov
+  - source: Мытищи
+    expected: Mytishchi
+  - source: Углич
+    expected: Uglich
+  - source: Дудинка
+    expected: Dudinka
+  - source: Фурманов
+    expected: Furmanov
+  - source: Уфа
+    expected: Ufa
+  - source: Хабаровск
+    expected: Khabarovsk
+  - source: Прохладный
+    expected: Prokhladnyǐ
+  - source: Цимлянск
+    expected: T͡Simli͡ansk
+  - source: Ельцин
+    expected: Elʹt͡sin
+  - source: Чебоксары
+    expected: Cheboksary
+  - source: Печора
+    expected: Pechora
+  - source: Шахтёрск
+    expected: Shakhtërsk
+  - source: Мышкин
+    expected: Myshkin
+  - source: Щёлково
+    expected: Shchëlkovo
+  - source: Ртищево
+    expected: Rtishchevo
+  - source: Подъездной
+    expected: Podʺezdnoǐ
+  - source: Ыттык-Кёль
+    expected: Yttyk-Këlʹ
+  - source: Тында
+    expected: Tynda
+  - source: Тюмень
+    expected: Ti͡umenʹ
+  - source: Электрогорск
+    expected: Ėlektrogorsk
+  - source: Радиоэлектроника
+    expected: Radioėlektronika
+  - source: Юбилейный
+    expected: I͡Ubileǐnyǐ
+  - source: Ключевская
+    expected: Kli͡uchevskai͡a
+  - source: Якутск
+    expected: I͡Akutsk
+  - source: Брянск
+    expected: Bri͡ansk
+
+map:
+  characters:
+    "\u0027": ""         # '
+    "\u0410": "A"        # А
+    "\u0411": "B"        # Б
+    "\u0412": "V"        # В
+    "\u0413": "G"        # Г
+    "\u0414": "D"        # Д
+    "\u0415": "E"        # Е
+    "\u0401": "Ë"        # Ё
+    "\u0416": "Zh"       # Ж
+    "\u0417": "Z"        # З
+    "\u0418": "I"        # И
+    "\u0419": "\u01CF"   # Й
+    "\u041A": "K"        # К
+    "\u041B": "L"        # Л
+    "\u041C": "M"        # М
+    "\u041D": "N"        # Н
+    "\u041E": "O"        # О
+    "\u041F": "P"        # П
+    "\u0420": "R"        # Р
+    "\u0421": "S"        # С
+    "\u0422": "T"        # Т
+    "\u0423": "U"        # У
+    "\u0424": "F"        # Ф
+    "\u0425": "Kh"       # Х
+    "\u0426": "T\u0361S" # Ц
+    "\u0427": "Ch"       # Ч
+    "\u0428": "Sh"       # Ш
+    "\u0429": "Shch"     # Щ
+    "\u042A": "ʺ"        # Ъ
+    "\u042B": "Y"        # Ы
+    "\u042C": "ʹ"        # Ь
+    "\u042D": "E\u0307"  # Э
+    "\u042E": "I\u0361U" # Ю
+    "\u042F": "I\u0361A" # Я
+
+    "\u0430": "a"        # а
+    "\u0431": "b"        # б
+    "\u0432": "v"        # в
+    "\u0433": "g"        # г
+    "\u0434": "d"        # д
+    "\u0435": "e"        # e
+    "\u0451": "ë"        # ё
+    "\u0436": "zh"       # ж
+    "\u0437": "z"        # з
+    "\u0438": "i"        # и
+    "\u0439": "\u01d0"   # й
+    "\u043A": "k"        # к
+    "\u043B": "l"        # л
+    "\u043C": "m"        # м
+    "\u043D": "n"        # н
+    "\u043E": "o"        # о
+    "\u043F": "p"        # п
+    "\u0440": "r"        # р
+    "\u0441": "s"        # с
+    "\u0442": "t"        # т
+    "\u0443": "u"        # у
+    "\u0444": "f"        # ф
+    "\u0445": "kh"       # х
+    "\u0446": "t\u0361s" # ц
+    "\u0447": "ch"       # ч
+    "\u0448": "sh"       # ш
+    "\u0449": "shch"     # щ
+    "\u044A": "ʺ"        # ъ
+    "\u044B": "y"        # ы
+    "\u044C": "ʹ"        # ь
+    "\u044D": "e\u0307"  # э
+    "\u044E": "i\u0361u" # ю
+    "\u044F": "i\u0361a" # я

data/maps/alalc-rus-Cyrl-Latn-2012.yaml

@@ -0,0 +1,162 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:rus
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization System 2012
+url: https://www.loc.gov/catdir/cpso/romanization/russian.pdf
+creation_date: 2012
+description: |
+  The ALA-LC Romanization tables for Slavic alphabets is a set of standards for romanization of texts
+  in various writing systems used in North American libraries and publications.
+  The latest version was published by the American Library Association and the Library of Congress in 2012.
+
+notes:
+  - 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.
+
+tests:
+  - source: Азов
+    expected: Azov
+  - source: Тамбов
+    expected: Tambov
+  - source: Барнаул
+    expected: Barnaul
+  - source: Кубань
+    expected: Kubanʹ
+  - source: Владимир
+    expected: Vladimir
+  - source: Ульяновск
+    expected: Ulʹi͡anovsk
+  - source: Грозный
+    expected: Groznyǐ
+  - source: Волгодонск
+    expected: Volgodonsk
+  - source: Дзержинский
+    expected: Dzerzhinskiǐ
+  - source: Нелидово
+    expected: Nelidovo
+  - source: Елизово
+    expected: Elizovo
+  - source: Чебоксары
+    expected: Cheboksary
+  - source: Ёлкин
+    expected: Ëlkin
+  - source: Озёрный
+    expected: Ozërnyǐ
+  - source: Жуков
+    expected: Zhukov
+  - source: Лужники
+    expected: Luzhniki
+  - source: Звенигород
+    expected: Zvenigorod
+  - source: Вязьма
+    expected: Vi͡azʹma
+  - source: Иркутск
+    expected: Irkutsk
+  - source: Апатиты
+    expected: Apatity
+  - source: Йошкар-Ола
+    expected: Ǐoshkar-Ola
+  - source: Бийск
+    expected: Biǐsk
+  - source: Киров
+    expected: Kirov
+  - source: Енисейск
+    expected: Eniseǐsk
+  - source: Ломоносов
+    expected: Lomonosov
+  - source: Нелидово
+    expected: Nelidovo
+  - source: Менделеев
+    expected: Mendeleev
+  - source: Каменка
+    expected: Kamenka
+  - source: Новосибирск
+    expected: Novosibirsk
+  - source: Кандалакша
+    expected: Kandalaksha
+  - source: Омск
+    expected: Omsk
+  - source: Красноярск
+    expected: Krasnoi͡arsk
+  - source: Петрозаводск
+    expected: Petrozavodsk
+  - source: Серпухов
+    expected: Serpukhov
+  - source: Ростов
+    expected: Rostov
+  - source: Северобайкальск
+    expected: Severobaǐkalʹsk
+  - source: Сковородино
+    expected: Skovorodino
+  - source: Чайковский
+    expected: Chaǐkovskiǐ
+  - source: Тамбов
+    expected: Tambov
+  - source: Мытищи
+    expected: Mytishchi
+  - source: Углич
+    expected: Uglich
+  - source: Дудинка
+    expected: Dudinka
+  - source: Фурманов
+    expected: Furmanov
+  - source: Уфа
+    expected: Ufa
+  - source: Хабаровск
+    expected: Khabarovsk
+  - source: Прохладный
+    expected: Prokhladnyǐ
+  - source: Цимлянск
+    expected: T͡Simli͡ansk
+  - source: Ельцин
+    expected: Elʹt͡sin
+  - source: Чебоксары
+    expected: Cheboksary
+  - source: Печора
+    expected: Pechora
+  - source: Шахтёрск
+    expected: Shakhtërsk
+  - source: Мышкин
+    expected: Myshkin
+  - source: Щёлково
+    expected: Shchëlkovo
+  - source: Ртищево
+    expected: Rtishchevo
+  - source: Подъездной
+    expected: Podʺezdnoǐ
+  - source: Ыттык-Кёль
+    expected: Yttyk-Këlʹ
+  - source: Тында
+    expected: Tynda
+  - source: Тюмень
+    expected: Ti͡umenʹ
+  - source: Электрогорск
+    expected: Ėlektrogorsk
+  - source: Радиоэлектроника
+    expected: Radioėlektronika
+  - source: Юбилейный
+    expected: I͡Ubileǐnyǐ
+  - source: Ключевская
+    expected: Kli͡uchevskai͡a
+  - source: Якутск
+    expected: I͡Akutsk
+  - source: Брянск
+    expected: Bri͡ansk
+
+map:
+  inherit: alalc-rus-Cyrl-Latn-1997
+
+  characters:
+    '\u0406': "\u012A"
+    '\u0456': "\u012B"
+
+    '\u0462': "I\u0361E" # Ѣ
+    '\u0463': "i\u0361e" # ѣ
+
+    '\u0472': "F\u0307" # Ѳ
+    '\u0473': "f\u0307" # ѳ
+
+    '\u0474': "Y\u0307" # Ѵ
+    '\u0475': "y\u0307" # ѵ